Triple

T16170731
Position Surface form Disambiguated ID Type / Status
Subject Andy Sipowicz E392426 entity
Predicate spouse P13 FINISHED
Object Sylvia Costas E536745 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: Sylvia Costas | Statement: [Andy Sipowicz, spouse, Sylvia Costas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sylvia Costas
Context triple: [Andy Sipowicz, spouse, Sylvia Costas]
  • A. Sylvia Costas chosen
    Sylvia Costas is a key supporting character on the television drama "NYPD Blue," known as an assistant district attorney and the love interest and later wife of Detective Andy Sipowicz.
  • B. Lea Greco
    Lea Greco is known as the wife of American jazz and pop singer-pianist Buddy Greco.
  • C. Mercedes Colomar
    Mercedes Colomar is a central character in the noir-inspired adventure game Grim Fandango, known as the virtuous and resourceful soul whom protagonist Manny Calavera strives to protect and accompany through the Land of the Dead.
  • D. Laura Barbieri
    Laura Barbieri is known as the wife of Argentine jazz saxophonist and composer Gato Barbieri.
  • E. Marlene Mathias
    Marlene Mathias is known as the daughter of American Olympic decathlon champion and politician Bob Mathias.
  • 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_69d87f1d32208190942e4e499a80c18c completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e21eb6de30819083af54b50ae5ae51 completed April 17, 2026, 11:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69fff7bd87f08190a9f2a1524e5db2ba completed May 10, 2026, 3:13 a.m.
Created at: April 10, 2026, 5:02 a.m.