Triple

T11800768
Position Surface form Disambiguated ID Type / Status
Subject Susannah Dean E280618 entity
Predicate hasDualPersonality P31337 FINISHED
Object Detta Walker E947901 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: Detta Walker | Statement: [Susannah Dean, hasDualPersonality, Detta Walker]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Detta Walker
Context triple: [Susannah Dean, hasDualPersonality, Detta Walker]
  • A. Detta Walker chosen
    Detta Walker is a fierce and volatile alternate personality of Susannah Dean in Stephen King’s The Dark Tower series.
  • B. Rachel Walker
    Rachel Walker was the second wife of American patriot Paul Revere, with whom she had a large family in colonial Boston.
  • C. Renee Walker
    Renee Walker is a fictional FBI agent and counterterrorism analyst from the television series "24," known for her intense dedication and morally complex decisions.
  • D. Kate Walker
    Kate Walker is the reserved, independent London woman who becomes the unexpected romantic interest of the title character in the film "Last Chance Harvey."
  • E. Kate Walker
    Kate Walker was a renowned 19th- and early 20th-century lighthouse keeper celebrated for her long and heroic service at Robbins Reef Lighthouse in New York Harbor.
  • 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_69d6ab258b808190b1735835c841e3a4 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8be15fb2481908f514781ce2c617f completed April 10, 2026, 9:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69f166dbcb848190a5942ec00a2ca2f9 completed April 29, 2026, 2:03 a.m.
Created at: April 8, 2026, 9:42 p.m.