Triple

T985220
Position Surface form Disambiguated ID Type / Status
Subject Love, Antosha E21262 entity
Predicate featuresInterviewee P17405 FINISHED
Object Zoe Saldana E117712 NE FINISHED

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: Zoe Saldana | Statement: [Love, Antosha, featuresInterviewee, Zoe Saldana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zoe Saldana
Context triple: [Love, Antosha, featuresInterviewee, Zoe Saldana]
  • A. Zoe Saldana chosen
    Zoe Saldana is an American actress known for her prominent roles in major science fiction and fantasy franchises, including Star Trek, Avatar, and the Marvel Cinematic Universe.
  • B. Kate Mara
    Kate Mara is an American actress known for her roles in films like "The Martian" and "Brokeback Mountain" and TV series such as "House of Cards."
  • C. Úrsula Corberó
    Úrsula Corberó is a Spanish actress best known internationally for her role as Tokyo in the hit television series "Money Heist."
  • D. Maya Hawke
    Maya Hawke is an American actress and singer best known for her breakout role as Robin Buckley in the Netflix series "Stranger Things."
  • E. Tessa Thompson
    Tessa Thompson is an American actress known for her versatile performances in film and television, including prominent roles in projects like "Creed," "Thor: Ragnarok," and "Westworld."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69a493c383dc8190a03257f22d4b4183 completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b75103688190a14342eef3842984 completed March 1, 2026, 10:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac2a14aec48190bc620cf492a82466 completed March 7, 2026, 1:37 p.m.
Created at: March 1, 2026, 7:41 p.m.