Triple

T9215002
Position Surface form Disambiguated ID Type / Status
Subject Martine Franck E221218 entity
Predicate workedFor P1910 FINISHED
Object Agence Vu
Agence Vu is a renowned French photography agency known for representing influential photojournalists and documentary photographers.
 E785561 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: Agence Vu | Statement: [Martine Franck, workedFor, Agence Vu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Agence Vu
Context triple: [Martine Franck, workedFor, Agence Vu]
  • A. Atelier du Midi
    Atelier du Midi is the French name for Vincent van Gogh’s “Studio of the South,” his envisioned artistic haven in Arles where he hoped to form a community of painters.
  • B. Voila
    "Voila" is a French-language album by American singer Belinda Carlisle that features her interpretations of classic French pop and chanson songs.
  • C. Dijon Productions
    Dijon Productions was a mid-20th-century American film production company best known for producing the 1958 crime drama "Thunder Road."
  • D. Studio La Cachette
    Studio La Cachette is a French animation studio known for its dynamic, hand-drawn 2D animation and work on high-profile projects and anthologies.
  • E. Vinci SA
    Vinci SA is a major French multinational concessions and construction company specializing in infrastructure development and management worldwide.
  • 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: Agence Vu
Triple: [Martine Franck, workedFor, Agence Vu]
Generated description
Agence Vu is a renowned French photography agency known for representing influential photojournalists and documentary photographers.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Agence Vu
Target entity description: Agence Vu is a renowned French photography agency known for representing influential photojournalists and documentary photographers.
  • A. Atelier du Midi
    Atelier du Midi is the French name for Vincent van Gogh’s “Studio of the South,” his envisioned artistic haven in Arles where he hoped to form a community of painters.
  • B. Voila
    "Voila" is a French-language album by American singer Belinda Carlisle that features her interpretations of classic French pop and chanson songs.
  • C. Dijon Productions
    Dijon Productions was a mid-20th-century American film production company best known for producing the 1958 crime drama "Thunder Road."
  • D. Studio La Cachette
    Studio La Cachette is a French animation studio known for its dynamic, hand-drawn 2D animation and work on high-profile projects and anthologies.
  • E. Vinci SA
    Vinci SA is a major French multinational concessions and construction company specializing in infrastructure development and management worldwide.
  • 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_69d0661c4c2c8190bc5be991a3a75f2b completed April 4, 2026, 1:15 a.m.
NEDg Description generation batch_69d0678b89ac8190b807e1c3b457a503 completed April 4, 2026, 1:21 a.m.
NED2 Entity disambiguation (via description) batch_69d0688d4c388190bb024b03cc86d08f completed April 4, 2026, 1:25 a.m.
Created at: March 30, 2026, 7:27 p.m.