Triple

T19754462
Position Surface form Disambiguated ID Type / Status
Subject The City & the City E474467 entity
Predicate mainCharacter P1183 FINISHED
Object Tyador Borlú 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: Tyador Borlú | Statement: [The City & the City, mainCharacter, Tyador Borlú]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tyador Borlú
Context triple: [The City & the City, mainCharacter, Tyador Borlú]
  • A. Inspector Tyador Borlú chosen
    Inspector Tyador Borlú is the central detective figure in China Miéville’s novel "The City & the City," known for investigating a murder that spans two overlapping, culturally distinct cities occupying the same physical space.
  • B. Trebor
    Trebor is a well-known confectionery brand, particularly recognized for its mints and boiled sweets.
  • C. Kylos
    Kylos is the destroyed home planet of Drax the Destroyer in the Marvel universe.
  • D. Marq Torien
    Marq Torien is an American rock singer and musician best known as the lead vocalist of the hard rock band BulletBoys and for his earlier work with several Los Angeles glam metal groups.
  • E. Herb Tarlek
    Herb Tarlek is a loud, tacky-suited, and comically inept advertising salesman character from the WKRP in Cincinnati television franchise.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e51940a0819087bd2996f98da668 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6529dada081909c5b4d65247c6032 completed April 20, 2026, 4:21 p.m.
Created at: April 10, 2026, 1:48 p.m.