Triple
T18273322
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AMM |
E437667
|
entity |
| Predicate | timeZone |
P109
|
FINISHED |
| Object |
Asia/Amman
Asia/Amman is the time zone used in Jordan’s capital city, Amman, representing the country’s standard local time.
|
E1315527
|
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: Asia/Amman | Statement: [AMM, timeZone, Asia/Amman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Asia/Amman Context triple: [AMM, timeZone, Asia/Amman]
-
A.
Asia/Damascus
Asia/Damascus is the IANA time zone identifier representing the local civil time observed in Damascus, Syria.
-
B.
Asia/Baghdad
Asia/Baghdad is the IANA time zone identifier representing the local time for Baghdad, Iraq.
-
C.
Asia/Hebron
Asia/Hebron is an IANA time zone identifier covering the Hebron area in the Palestinian territories, typically aligned with Eastern European Time and its daylight saving adjustments.
-
D.
Asia/Qatar
Asia/Qatar is the IANA time zone identifier representing the standard time observed throughout the country of Qatar in Western Asia.
-
E.
Asia/Bahrain
Asia/Bahrain is an IANA time zone identifier representing the standard time observed in the Kingdom of Bahrain in the Arabian Gulf region.
- 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: Asia/Amman Triple: [AMM, timeZone, Asia/Amman]
Generated description
Asia/Amman is the time zone used in Jordan’s capital city, Amman, representing the country’s standard local time.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Asia/Amman Target entity description: Asia/Amman is the time zone used in Jordan’s capital city, Amman, representing the country’s standard local time.
-
A.
Asia/Damascus
Asia/Damascus is the IANA time zone identifier representing the local civil time observed in Damascus, Syria.
-
B.
Asia/Baghdad
Asia/Baghdad is the IANA time zone identifier representing the local time for Baghdad, Iraq.
-
C.
Asia/Hebron
Asia/Hebron is an IANA time zone identifier covering the Hebron area in the Palestinian territories, typically aligned with Eastern European Time and its daylight saving adjustments.
-
D.
Asia/Qatar
Asia/Qatar is the IANA time zone identifier representing the standard time observed throughout the country of Qatar in Western Asia.
-
E.
Asia/Bahrain
Asia/Bahrain is an IANA time zone identifier representing the standard time observed in the Kingdom of Bahrain in the Arabian Gulf region.
- 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_69d8b914530c8190b4474d862a2b2a1b |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e5005006108190bbddddbe6bbdc911 |
completed | April 19, 2026, 4:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a03b3fc2a808190be07b43e9e7ac3bb |
completed | May 12, 2026, 11:13 p.m. |
| NEDg | Description generation | batch_6a03b53fc3688190aa6f8e9673763e79 |
completed | May 12, 2026, 11:18 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a03b62cb67481908c78ca4d55710dbd |
completed | May 12, 2026, 11:22 p.m. |
Created at: April 10, 2026, 10:34 a.m.