Triple

T19276096
Position Surface form Disambiguated ID Type / Status
Subject Town of Colma E482057 entity
Predicate nickname P55 FINISHED
Object City of Souls 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: City of Souls | Statement: [Town of Colma, nickname, City of Souls]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: City of Souls
Context triple: [Town of Colma, nickname, City of Souls]
  • A. City of Souls chosen
    City of Souls is the somber nickname for Colma, California, a small town famous for its vast cemeteries and far larger population of the dead than the living.
  • B. City of Ghosts
    City of Ghosts is a 2002 neo-noir crime drama film set largely in Cambodia, following a con man entangled in a dangerous underworld scheme.
  • C. Library of Souls
    Library of Souls is a dark fantasy novel by Ransom Riggs that continues the story of peculiar children as they confront sinister forces in a richly atmospheric, time-bending world.
  • D. All Souls
    All Souls is a Christian feast day commemorating the faithful departed, particularly observed in Western churches on November 2.
  • E. All Souls
    All Souls is a short-lived supernatural drama television series centered on eerie occurrences at a haunted Boston hospital.
  • 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_69d8e8ce54cc8190998418ff1f66ef28 completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5fbbbdf3481909abb46c71f64106a completed April 20, 2026, 10:11 a.m.
Created at: April 10, 2026, 1:29 p.m.