Triple
T13357684
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Émile Combes |
E318736
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Combes |
E796247
|
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: Combes | Statement: [Émile Combes, familyName, Combes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Combes Context triple: [Émile Combes, familyName, Combes]
-
A.
Combes
chosen
Combes is the maiden surname of American actress Barbara Billingsley, best known for her role as June Cleaver on the classic TV series "Leave It to Beaver."
-
B.
Cazeneuve
Cazeneuve is a French surname most notably borne by Bernard Cazeneuve, a prominent French politician and former Prime Minister of France.
-
C.
Cambon
Cambon is a French surname most notably associated with influential diplomats and politicians such as Paul Cambon.
-
D.
Boucicaut
Boucicaut is a station on the Paris Métro serving the 15th arrondissement of Paris.
-
E.
Déchevaux-Dumesnil
Déchevaux-Dumesnil is a French surname most notably borne by Suzanne Déchevaux-Dumesnil, the longtime partner and later wife of writer Samuel Beckett.
- 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_69d806b7bbac8190b85278c87fa7aff3 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69da62887e588190bd7241c720a112a2 |
completed | April 11, 2026, 3:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f72677b2a48190aad30f3ee6cacefb |
completed | May 3, 2026, 10:41 a.m. |
Created at: April 9, 2026, 9:32 p.m.