Triple

T36589075
Position Surface form Disambiguated ID Type / Status
Subject Carolina López E902615 entity
Predicate sharedAdultLifeWith P196375 FINISHED
Object Roberto Bolaño NE NERFINISHED

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: Roberto Bolaño | Statement: [Carolina López, sharedAdultLifeWith, Roberto Bolaño]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: sharedAdultLifeWith
Context triple: [Carolina López, sharedAdultLifeWith, Roberto Bolaño]
  • A. sharedLaterLifeWith
    Indicates that two entities spent a significant portion of their later life period together, sharing circumstances, experiences, or close association during that time.
  • B. hasAdultLifeIn
    Indicates that an entity spends or experiences its adult stage of life within a specified location or environment.
  • C. hasParallelLifeWith
    Indicates that two entities lead or experience lives that run alongside each other in similar, corresponding, or contemporaneous ways without fully intersecting.
  • D. sexLaterInStory
    Indicates that the entities engage in sexual activity at a later point in the narrative or storyline.
  • E. involvesRealLifeRelationship chosen
    Indicates a relationship where the connected entities are engaged in or depict an actual, non-fictional interpersonal relationship that exists or existed in real life.
  • F. None of above.

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_69f76e6592e88190bac4eb00a46e9df9 completed May 3, 2026, 3:48 p.m.
NER Named-entity recognition batch_6a009a0e1fa481909ed881012009b268 completed May 10, 2026, 2:45 p.m.
PD Predicate disambiguation batch_6a0092e9fcb08190a966d720684f25ec completed May 10, 2026, 2:15 p.m.
Created at: May 3, 2026, 4:11 p.m.