Triple

T14779828
Position Surface form Disambiguated ID Type / Status
Subject In Secret E347360 entity
Predicate mainCharacter P1183 FINISHED
Object Laurent
Laurent is the central protagonist of the film "In Secret," a dark romantic thriller based on Émile Zola’s novel "Thérèse Raquin."
 E370200 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: Laurent | Statement: [In Secret, mainCharacter, Laurent]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Laurent
Context triple: [In Secret, mainCharacter, Laurent]
  • A. Laurent
    Laurent is a Belgian prince, the younger son of King Albert II and Queen Paola, known for his environmental interests and occasional public controversies.
  • B. Laurent
    Laurent is a nomadic vampire in the Twilight series who initially allies with James and Victoria before later attempting to betray the Cullens.
  • C. Laurent
    Laurent is a French surname historically associated with various notable figures and families.
  • D. Laurent
    Laurent is a French given name, commonly used as the French form of Lawrence.
  • E. Laurent
    Laurent is a central figure in Émile Zola’s novel "Thérèse Raquin," known as Thérèse’s lover and accomplice in a dark, psychologically driven crime.
  • 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: Laurent
Triple: [In Secret, mainCharacter, Laurent]
Generated description
Laurent is the central protagonist of the film "In Secret," a dark romantic thriller based on Émile Zola’s novel "Thérèse Raquin."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Laurent
Target entity description: Laurent is the central protagonist of the film "In Secret," a dark romantic thriller based on Émile Zola’s novel "Thérèse Raquin."
  • A. Laurent
    Laurent is a Belgian prince, the younger son of King Albert II and Queen Paola, known for his environmental interests and occasional public controversies.
  • B. Laurent chosen
    Laurent is a central figure in Émile Zola’s novel "Thérèse Raquin," known as Thérèse’s lover and accomplice in a dark, psychologically driven crime.
  • C. Laurent
    Laurent is a nomadic vampire in the Twilight series who initially allies with James and Victoria before later attempting to betray the Cullens.
  • D. Laurent
    Laurent is a French surname historically associated with various notable figures and families.
  • E. Laurent
    Laurent is a French given name, commonly used as the French form of Lawrence.
  • F. None of above.

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_69d822e9b9e08190bedcc31a163fda82 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deca9c7cac8190ba900df95e42e318 completed April 14, 2026, 11:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe9683d34c81909ff7486582766620 completed May 9, 2026, 2:05 a.m.
NEDg Description generation batch_69fe972728dc8190a9cf2a3e984b05a7 completed May 9, 2026, 2:08 a.m.
NED2 Entity disambiguation (via description) batch_69fe9790d1d081908fc94829d3104e07 completed May 9, 2026, 2:10 a.m.
Created at: April 10, 2026, 1:31 a.m.