Triple
T13310259
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | La Marche de l'empereur |
E317041
|
entity |
| Predicate | productionCompany |
P490
|
FINISHED |
| Object | Bonne Pioche |
E317047
|
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: Bonne Pioche | Statement: [La Marche de l'empereur, productionCompany, Bonne Pioche]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bonne Pioche Context triple: [La Marche de l'empereur, productionCompany, Bonne Pioche]
-
A.
Bonne Pioche
chosen
Bonne Pioche is a French film and television production company known internationally for producing acclaimed documentaries such as "March of the Penguins."
-
B.
Chapotel
Chapotel is a French surname associated with individuals such as Rose Chapotel.
-
C.
La Sablonière
La Sablonière is one of the small islets within the Les Écréhous reef and island group off the coast of Jersey in the Channel Islands.
-
D.
Le Tote
Le Tote is a fashion rental subscription service company that expanded into traditional retail by acquiring the historic department store chain Lord & Taylor.
-
E.
Le Bonheur
Le Bonheur is a philosophical poetry collection by French poet and Nobel laureate Sully Prudhomme that meditates on the nature and pursuit of human happiness.
- 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_69d806b40ab4819094adf6c374f4811a |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d990f56abc8190951774a999e2ce11 |
completed | April 11, 2026, 12:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f716e7b9a48190a33b04df8ad45ed8 |
completed | May 3, 2026, 9:35 a.m. |
Created at: April 9, 2026, 9:29 p.m.