Triple
T8514434
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | RSMC Anchorage (volcanic ash advisory centre) |
E201536
|
entity |
| Predicate | relatedTo |
P37
|
FINISHED |
| Object |
RSMC Johannesburg (volcanic ash advisory centre)
RSMC Johannesburg (volcanic ash advisory centre) is a specialized meteorological center responsible for monitoring volcanic ash in its designated airspace region and issuing advisories to support aviation safety.
|
E738761
|
NE FINISHED |
How this triple was built (4 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: RSMC Johannesburg (volcanic ash advisory centre) | Statement: [RSMC Anchorage (volcanic ash advisory centre), relatedTo, RSMC Johannesburg (volcanic ash advisory centre)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: RSMC Johannesburg (volcanic ash advisory centre) Context triple: [RSMC Anchorage (volcanic ash advisory centre), relatedTo, RSMC Johannesburg (volcanic ash advisory centre)]
-
A.
RSMC Wellington (volcanic ash advisory centre)
RSMC Wellington (volcanic ash advisory centre) is a specialized meteorological center responsible for monitoring and issuing advisories on volcanic ash clouds to support aviation safety in its designated region.
-
B.
RSMC Buenos Aires (volcanic ash advisory centre)
RSMC Buenos Aires is a specialized meteorological center that monitors volcanic activity and issues volcanic ash advisories to support aviation safety and regional hazard management.
-
C.
RSMC Tokyo (volcanic ash advisory centre)
RSMC Tokyo (volcanic ash advisory centre) is a specialized meteorological center in Japan responsible for monitoring volcanic activity and issuing international volcanic ash advisories for aviation safety in its designated region.
-
D.
RSMC London (volcanic ash advisory centre)
RSMC London (volcanic ash advisory centre) is a specialized meteorological center operated by the UK Met Office that monitors volcanic eruptions and issues international volcanic ash advisories for aviation safety.
-
E.
RSMC Darwin (volcanic ash advisory centre)
RSMC Darwin is a World Meteorological Organization-designated Volcanic Ash Advisory Centre responsible for monitoring and issuing warnings about volcanic ash clouds in its assigned region, particularly over parts of Australia and Southeast Asia.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: RSMC Johannesburg (volcanic ash advisory centre) Triple: [RSMC Anchorage (volcanic ash advisory centre), relatedTo, RSMC Johannesburg (volcanic ash advisory centre)]
Generated description
RSMC Johannesburg (volcanic ash advisory centre) is a specialized meteorological center responsible for monitoring volcanic ash in its designated airspace region and issuing advisories to support aviation safety.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: RSMC Johannesburg (volcanic ash advisory centre) Target entity description: RSMC Johannesburg (volcanic ash advisory centre) is a specialized meteorological center responsible for monitoring volcanic ash in its designated airspace region and issuing advisories to support aviation safety.
-
A.
RSMC Wellington (volcanic ash advisory centre)
RSMC Wellington (volcanic ash advisory centre) is a specialized meteorological center responsible for monitoring and issuing advisories on volcanic ash clouds to support aviation safety in its designated region.
-
B.
RSMC Buenos Aires (volcanic ash advisory centre)
RSMC Buenos Aires is a specialized meteorological center that monitors volcanic activity and issues volcanic ash advisories to support aviation safety and regional hazard management.
-
C.
RSMC Tokyo (volcanic ash advisory centre)
RSMC Tokyo (volcanic ash advisory centre) is a specialized meteorological center in Japan responsible for monitoring volcanic activity and issuing international volcanic ash advisories for aviation safety in its designated region.
-
D.
RSMC London (volcanic ash advisory centre)
RSMC London (volcanic ash advisory centre) is a specialized meteorological center operated by the UK Met Office that monitors volcanic eruptions and issues international volcanic ash advisories for aviation safety.
-
E.
RSMC Darwin (volcanic ash advisory centre)
RSMC Darwin is a World Meteorological Organization-designated Volcanic Ash Advisory Centre responsible for monitoring and issuing warnings about volcanic ash clouds in its assigned region, particularly over parts of Australia and Southeast Asia.
- F. None of above. chosen
Provenance (5 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ca8320e5748190ac2c585a0bba8193 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe60e12848190a4a3dfa457aef275 |
completed | March 31, 2026, 3:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce4e56ef088190b4f938486bbb7962 |
completed | April 2, 2026, 11:09 a.m. |
| NEDg | Description generation | batch_69ce4ffac8a08190bc2131c0d260ca39 |
completed | April 2, 2026, 11:16 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ce5117c7508190b74821d029d226c6 |
completed | April 2, 2026, 11:20 a.m. |
Created at: March 30, 2026, 6:15 p.m.