Triple
T13651497
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Serge Haroche |
E326748
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Haroche |
E326748
|
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: Haroche | Statement: [Serge Haroche, familyName, Haroche]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Haroche Context triple: [Serge Haroche, familyName, Haroche]
-
A.
Haroche
chosen
Haroche is a French surname most notably associated with Nobel Prize–winning physicist Serge Haroche.
-
B.
Balard
Balard is a Paris Métro station in the 15th arrondissement, serving as a key transport hub near the Parc des Expositions and several major administrative and military sites.
-
C.
Barbaroux
Barbaroux is a French surname most notably associated with Charles Barbaroux, a prominent figure of the French Revolution.
-
D.
Bidault
Bidault is a French surname most notably associated with Georges Bidault, a prominent mid-20th-century French politician and statesman.
-
E.
Crozat
Crozat is a notable French aristocratic and financier family prominent in the 17th and 18th centuries, known for its immense wealth, art collections, and influence at the royal court.
- 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_69d8076d8270819092afc2f0e9c359a8 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbc609676c8190b5b1cabe6b315142 |
completed | April 12, 2026, 4:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f78affa3c481909dba71e2ce9f44c1 |
completed | May 3, 2026, 5:50 p.m. |
Created at: April 9, 2026, 9:52 p.m.