Triple
T14455748
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Delicacy |
E358454
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object |
Marc-Antoine Robert
Marc-Antoine Robert is a French film producer known for his work on acclaimed contemporary cinema.
|
E1125135
|
NE FINISHED |
How this triple was built (4 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: Marc-Antoine Robert | Statement: [Delicacy, producer, Marc-Antoine Robert]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marc-Antoine Robert Context triple: [Delicacy, producer, Marc-Antoine Robert]
-
A.
Benoît Gabriel
Benoît Gabriel is a member of the notable Gabriel family of French architects, known for their influential contributions to classical architecture.
-
B.
Antoine Daniel
Antoine Daniel was a 17th-century French Jesuit missionary and martyr who worked among Indigenous peoples in New France (present-day Canada).
-
C.
Pierre-Louis
Pierre-Louis is a French given name commonly used as a compound first name in Francophone countries.
-
D.
François Lecointre
François Lecointre is a French Army general who served as France’s Chief of the Defence Staff.
-
E.
Sébastien Eugène
Sébastien Eugène is a French local politician who serves as the mayor of the town of Château-Thierry in northern France.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Marc-Antoine Robert Triple: [Delicacy, producer, Marc-Antoine Robert]
Generated description
Marc-Antoine Robert is a French film producer known for his work on acclaimed contemporary cinema.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Marc-Antoine Robert Target entity description: Marc-Antoine Robert is a French film producer known for his work on acclaimed contemporary cinema.
-
A.
Benoît Gabriel
Benoît Gabriel is a member of the notable Gabriel family of French architects, known for their influential contributions to classical architecture.
-
B.
Antoine Daniel
Antoine Daniel was a 17th-century French Jesuit missionary and martyr who worked among Indigenous peoples in New France (present-day Canada).
-
C.
Pierre-Louis
Pierre-Louis is a French given name commonly used as a compound first name in Francophone countries.
-
D.
François Lecointre
François Lecointre is a French Army general who served as France’s Chief of the Defence Staff.
-
E.
Sébastien Eugène
Sébastien Eugène is a French local politician who serves as the mayor of the town of Château-Thierry in northern France.
- F. None of above. chosen
Provenance (5 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_69d82794dfa081909b9134ad2e32244b |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de91a9c0d48190ae015e5e0db806ca |
completed | April 14, 2026, 7:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe6b3a76ac819088587b9fa560b6dc |
completed | May 8, 2026, 11:01 p.m. |
| NEDg | Description generation | batch_69fe6df63b78819087d6c709db1ce889 |
completed | May 8, 2026, 11:12 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69fe6e32f7a0819086ca1303024c6db9 |
completed | May 8, 2026, 11:13 p.m. |
Created at: April 10, 2026, 1:19 a.m.