Triple
T12933978
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pierre Mauroy |
E309454
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Mauroy |
E309454
|
NE FINISHED |
How this triple was built (2 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: Mauroy | Statement: [Pierre Mauroy, familyName, Mauroy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mauroy Context triple: [Pierre Mauroy, familyName, Mauroy]
-
A.
Mauroy
chosen
Mauroy is a French surname most notably associated with Pierre Mauroy, a former Prime Minister of France and prominent Socialist politician.
-
B.
Gilbert Romme
Gilbert Romme was a French revolutionary politician and mathematician best known for overseeing the creation of the French Republican Calendar.
-
C.
Jean-Marie Meunier
Jean-Marie Meunier is a person bearing the surname Meunier, though no widely known public information distinguishes him beyond this association.
-
D.
Barthélemy
Barthélemy is the given name of Barthélemy Catherine Joubert, a French general who served during the Revolutionary Wars.
-
E.
Daniel Pomarède
Daniel Pomarède is a French astrophysicist known for his work in cosmography and for helping map and characterize large-scale structures of the universe, including major galaxy superclusters.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d7bdfa933c8190b5a27aa4a08a19b7 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d97dc6517481908637781da240b51f |
completed | April 10, 2026, 10:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6af6a830881908ab238b250d2c7d5 |
completed | May 3, 2026, 2:14 a.m. |
Created at: April 9, 2026, 5:42 p.m.