Triple

T21581007
Position Surface form Disambiguated ID Type / Status
Subject John Bell Hood E532521 entity
Predicate familyName P18 FINISHED
Object Hood 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: Hood | Statement: [John Bell Hood, familyName, Hood]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hood
Context triple: [John Bell Hood, familyName, Hood]
  • A. Hood
    "Hood" is a novel by Emma Donoghue that explores grief, identity, and a lesbian relationship in contemporary Ireland.
  • B. Hood chosen
    Hood is an English surname historically associated with notable figures such as the British naval commander Samuel Hood, 1st Viscount Hood.
  • C. Hood
    Hood is a Marvel Comics supervillain and crime boss who uses mystical powers and underworld connections to challenge heroes and rival kingpins like Wilson Fisk.
  • D. HOOD
    HOOD is the stock ticker symbol for Robinhood Markets, Inc., a financial services company known for its commission-free trading app for stocks, ETFs, options, and cryptocurrencies.
  • E. Hoodi
    Hoodi is a rapidly developing suburban neighborhood in eastern Bengaluru, India, known for its residential complexes, tech parks, and proximity to major IT hubs.
  • 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_69e0c4618bec8190bcb0feb74568cbb1 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69eeeb5c496c819093113dd5790fca48 completed April 27, 2026, 4:51 a.m.
Created at: April 16, 2026, 6:31 p.m.