Triple

T17912757
Position Surface form Disambiguated ID Type / Status
Subject Black Hand E447852 entity
Predicate baseOfOperations P2591 FINISHED
Object Coast City 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: Coast City | Statement: [Black Hand, baseOfOperations, Coast City]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Coast City
Context triple: [Black Hand, baseOfOperations, Coast City]
  • A. Coast City chosen
    Coast City is a major fictional American coastal metropolis in the DC Universe, best known as the longtime home of Green Lantern Hal Jordan.
  • B. Beach City
    Beach City is the small coastal town in the animated series "Steven Universe," known as the home of Steven, the Crystal Gems, and many of the show's central events.
  • C. Verona Beach
    Verona Beach is the modern, stylized coastal city that serves as the backdrop for Baz Luhrmann’s 1996 film adaptation of Shakespeare’s "Romeo + Juliet."
  • D. Bayside
    Bayside is a primarily residential neighborhood in the northeastern part of Queens, New York City, known for its suburban feel, good schools, and waterfront parks.
  • E. Bayside
    Bayside is a neighborhood in Portland, Maine, known for its mix of residential, commercial, and light industrial areas just west of East Bayside.
  • 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_69d8b9f6d394819082a6d69fd1e23d2f completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4a30288ac8190bc633e69447709bf completed April 19, 2026, 9:40 a.m.
Created at: April 10, 2026, 10:19 a.m.