Triple
T15053364
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oberhausen |
E379422
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object |
Carbonia
Carbonia is an industrial town in southwestern Sardinia, Italy, historically known for its coal mining industry.
|
E1135383
|
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: Carbonia | Statement: [Oberhausen, hasTwinTown, Carbonia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Carbonia Context triple: [Oberhausen, hasTwinTown, Carbonia]
-
A.
Argiletum
Argiletum was an ancient street in Rome that connected the Roman Forum to the Subura district and later became partly occupied by the Forum of Nerva.
-
B.
Galatrona
Galatrona is a small locality within the municipality of Bucine in the Tuscany region of Italy, known for its rural landscape and historic surroundings.
-
C.
Serdiana
Serdiana is a small municipality in southern Sardinia, Italy, known for its rural landscape and wine production.
-
D.
Agira
Agira is a historic hill town in central Sicily, Italy, known for its ancient origins, medieval architecture, and panoramic views over the surrounding countryside.
-
E.
Copparo
Copparo is a municipality in Italy’s Emilia-Romagna region, known for its agricultural economy and location within the Po Valley near the city of Ferrara.
- 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: Carbonia Triple: [Oberhausen, hasTwinTown, Carbonia]
Generated description
Carbonia is an industrial town in southwestern Sardinia, Italy, historically known for its coal mining industry.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Carbonia Target entity description: Carbonia is an industrial town in southwestern Sardinia, Italy, historically known for its coal mining industry.
-
A.
Argiletum
Argiletum was an ancient street in Rome that connected the Roman Forum to the Subura district and later became partly occupied by the Forum of Nerva.
-
B.
Galatrona
Galatrona is a small locality within the municipality of Bucine in the Tuscany region of Italy, known for its rural landscape and historic surroundings.
-
C.
Serdiana
Serdiana is a small municipality in southern Sardinia, Italy, known for its rural landscape and wine production.
-
D.
Agira
Agira is a historic hill town in central Sicily, Italy, known for its ancient origins, medieval architecture, and panoramic views over the surrounding countryside.
-
E.
Copparo
Copparo is a municipality in Italy’s Emilia-Romagna region, known for its agricultural economy and location within the Po Valley near the city of Ferrara.
- 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_69d85cd64d108190853797a95c11cc45 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69deda92091c81909180f486edf01405 |
completed | April 15, 2026, 12:23 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fea5bdeee48190949b0fe63eb6a21a |
completed | May 9, 2026, 3:10 a.m. |
| NEDg | Description generation | batch_69fea79dd1bc8190ae1ac5edad3db9cb |
completed | May 9, 2026, 3:18 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69fea83aaff48190af7a7399e40fdf46 |
completed | May 9, 2026, 3:21 a.m. |
Created at: April 10, 2026, 3:01 a.m.