Triple
T9215104
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Henri Cartier-Bresson Foundation |
E221222
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object |
Agnès Sire
Agnès Sire is a French photography curator and director closely associated with preserving and promoting the legacy of Henri Cartier-Bresson.
|
E811340
|
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: Agnès Sire | Statement: [Henri Cartier-Bresson Foundation, foundedBy, Agnès Sire]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Agnès Sire Context triple: [Henri Cartier-Bresson Foundation, foundedBy, Agnès Sire]
-
A.
Agnès Guillemot
Agnès Guillemot was a French film editor known for her work on influential New Wave and art-house films, including collaborations with directors such as Jean-Luc Godard.
-
B.
Françoise Noguès
Françoise Noguès is a French physician best known as the mother of Brigitte Macron, the First Lady of France.
-
C.
Nathalie Soulié
Nathalie Soulié is a French woman best known as the former spouse of politician and ex–Prime Minister of France Manuel Valls.
-
D.
Brigitte Fouré
Brigitte Fouré is a French politician known for serving as the mayor of the city of Amiens.
-
E.
Agnès Godard
Agnès Godard is a renowned French cinematographer celebrated for her long-standing collaboration with director Claire Denis and her distinctive, atmospheric visual style.
- 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: Agnès Sire Triple: [Henri Cartier-Bresson Foundation, foundedBy, Agnès Sire]
Generated description
Agnès Sire is a French photography curator and director closely associated with preserving and promoting the legacy of Henri Cartier-Bresson.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Agnès Sire Target entity description: Agnès Sire is a French photography curator and director closely associated with preserving and promoting the legacy of Henri Cartier-Bresson.
-
A.
Agnès Guillemot
Agnès Guillemot was a French film editor known for her work on influential New Wave and art-house films, including collaborations with directors such as Jean-Luc Godard.
-
B.
Françoise Noguès
Françoise Noguès is a French physician best known as the mother of Brigitte Macron, the First Lady of France.
-
C.
Nathalie Soulié
Nathalie Soulié is a French woman best known as the former spouse of politician and ex–Prime Minister of France Manuel Valls.
-
D.
Brigitte Fouré
Brigitte Fouré is a French politician known for serving as the mayor of the city of Amiens.
-
E.
Agnès Godard
Agnès Godard is a renowned French cinematographer celebrated for her long-standing collaboration with director Claire Denis and her distinctive, atmospheric visual style.
- 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_69ca83eae42c8190a0ea9e040710a277 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccda0830a8819096a186ed2e976cba |
completed | April 1, 2026, 8:40 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1820133348190a25ba1ab3fc7359d |
completed | April 4, 2026, 9:26 p.m. |
| NEDg | Description generation | batch_69d182cb723881909f29b6a875e99da1 |
completed | April 4, 2026, 9:29 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d1833692788190990ad426b6502488 |
completed | April 4, 2026, 9:31 p.m. |
Created at: March 30, 2026, 7:27 p.m.