Triple

T21814417
Position Surface form Disambiguated ID Type / Status
Subject Eddie Fisher E538562 entity
Predicate spouse P13 FINISHED
Object Betty Lin 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: Betty Lin | Statement: [Eddie Fisher, spouse, Betty Lin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Betty Lin
Context triple: [Eddie Fisher, spouse, Betty Lin]
  • A. Betty Lin chosen
    Betty Lin was the fourth wife of American singer Eddie Fisher, known primarily for her marriage to the popular entertainer.
  • B. Nena Hsu
    Nena Hsu is a film editor known for her work on the teen heist comedy "The Perfect Score."
  • C. Susan Chan
    Susan Chan is a screenwriter known for her work on the 1998 film "Who Am I?" starring Jackie Chan.
  • D. Sun Li-jen
    Sun Li-jen was a prominent Chinese Nationalist general renowned for his leadership in World War II, particularly in the Burma Campaign against Japanese forces.
  • E. Song Meiling
    Song Meiling was a prominent 20th-century Chinese political figure and influential wife of Chiang Kai-shek, known for her diplomatic efforts, advocacy for China on the international stage, and significant role in modern Chinese history.
  • 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_69e0c473f0f8819086c9d1b4a143bd67 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f07cc8e6808190bde4d0e0981e4117 completed April 28, 2026, 9:24 a.m.
Created at: April 16, 2026, 6:54 p.m.