Triple
T10470205
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Before Night Falls |
E246903
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Olivier Martinez |
E391831
|
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: Olivier Martinez | Statement: [Before Night Falls, starring, Olivier Martinez]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Olivier Martinez Context triple: [Before Night Falls, starring, Olivier Martinez]
-
A.
Olivier Martinez
chosen
Olivier Martinez is a French actor known for his roles in films such as "Unfaithful," "Before Night Falls," and "S.W.A.T."
-
B.
Olivier Bousquet
Olivier Bousquet is a French computer scientist and machine learning researcher known for his work on statistical learning theory and his leadership roles in industry AI research.
-
C.
Olivier Gacquerre
Olivier Gacquerre is a French politician who serves as the mayor of the northern French city of Béthune.
-
D.
Laurent Rossi
Laurent Rossi is the son of famed French singer and actor Tino Rossi, known primarily for his connection to his father's legacy in French popular culture.
-
E.
Arnaud Decagny
Arnaud Decagny is a French local politician who serves as the mayor of the northern town of Maubeuge.
- 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_69d381c16c248190a2fe5b471e584e9c |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d509305fec81908b1acd91ae1f875d |
completed | April 7, 2026, 1:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d8dc68b49481909715c36a4c0e7c4f |
completed | April 10, 2026, 11:18 a.m. |
Created at: April 6, 2026, 12:20 p.m.