Triple
T9999790
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spectral |
E197293
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Nic Mathieu |
E197293
|
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: Nic Mathieu | Statement: [Spectral, director, Nic Mathieu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nic Mathieu Context triple: [Spectral, director, Nic Mathieu]
-
A.
Nic Mathieu
chosen
Nic Mathieu is a film director best known for helming the science fiction action movie "Spectral."
-
B.
Tyrann Mathieu
Tyrann Mathieu is an American football safety and return specialist, nicknamed the "Honey Badger," known for his playmaking ability, versatility, and impact on defenses in both college and the NFL.
-
C.
Mathieu Froment
Mathieu Froment is the central character of Émile Zola’s novel "Fécondité," embodying the author’s exploration of family, morality, and social responsibility in turn-of-the-century France.
-
D.
Mathias Moncorgé
Mathias Moncorgé is a French actor and horse racing professional, best known as the son of legendary film star Jean Gabin.
-
E.
Damien Meslot
Damien Meslot is a French politician who serves as the mayor of Belfort and has been active in national and local politics.
- 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_69ca82f3b61c81908ecc2c1c96dbc2e4 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdcc8dc9c081909b6d20909ada09cf |
completed | April 2, 2026, 1:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d2584bd6cc8190841353847dd2f00c |
completed | April 5, 2026, 12:40 p.m. |
Created at: March 30, 2026, 8:51 p.m.