Triple
T9043457
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nérac |
E216695
|
entity |
| Predicate | hasMayor |
P185
|
FINISHED |
| Object |
Nicolas Lacombe
Nicolas Lacombe is a French local politician who serves as the mayor of the town of Nérac in southwestern France.
|
E798734
|
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: Nicolas Lacombe | Statement: [Nérac, hasMayor, Nicolas Lacombe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nicolas Lacombe Context triple: [Nérac, hasMayor, Nicolas Lacombe]
-
A.
Nicolas Dufourcq
Nicolas Dufourcq is a French business executive known for leading major technology and finance institutions, including serving as chairman of semiconductor company STMicroelectronics.
-
B.
Nicolas Bérauld
Nicolas Bérauld was a French Renaissance humanist scholar and teacher known for mentoring figures such as the printer and humanist Étienne Dolet.
-
C.
Yannick Jauzion
Yannick Jauzion is a retired French rugby union centre renowned for his powerful running, playmaking skills, and key role in France’s national team during the 2000s.
-
D.
Laurent Vastel
Laurent Vastel is a French local politician who serves as the mayor of the Paris suburb Fontenay-aux-Roses.
-
E.
Matthieu Rougé
Matthieu Rougé is a French Roman Catholic prelate who serves as the bishop of the Diocese of Nanterre.
- 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: Nicolas Lacombe Triple: [Nérac, hasMayor, Nicolas Lacombe]
Generated description
Nicolas Lacombe is a French local politician who serves as the mayor of the town of Nérac in southwestern France.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Nicolas Lacombe Target entity description: Nicolas Lacombe is a French local politician who serves as the mayor of the town of Nérac in southwestern France.
-
A.
Nicolas Dufourcq
Nicolas Dufourcq is a French business executive known for leading major technology and finance institutions, including serving as chairman of semiconductor company STMicroelectronics.
-
B.
Nicolas Bérauld
Nicolas Bérauld was a French Renaissance humanist scholar and teacher known for mentoring figures such as the printer and humanist Étienne Dolet.
-
C.
Yannick Jauzion
Yannick Jauzion is a retired French rugby union centre renowned for his powerful running, playmaking skills, and key role in France’s national team during the 2000s.
-
D.
Laurent Vastel
Laurent Vastel is a French local politician who serves as the mayor of the Paris suburb Fontenay-aux-Roses.
-
E.
Matthieu Rougé
Matthieu Rougé is a French Roman Catholic prelate who serves as the bishop of the Diocese of Nanterre.
- 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_69ca83d22d488190adbce5e020e9cd1d |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc6b1228748190be0c4afe6e0bd9a3 |
completed | April 1, 2026, 12:47 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d110090f208190bf0338a37bb28e8b |
completed | April 4, 2026, 1:20 p.m. |
| NEDg | Description generation | batch_69d110bb55488190955c18087aceecb8 |
completed | April 4, 2026, 1:23 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d11113db48819083a7da54f72326a6 |
completed | April 4, 2026, 1:24 p.m. |
Created at: March 30, 2026, 7:09 p.m.