Triple

T5787802
Position Surface form Disambiguated ID Type / Status
Subject Mel Tormé E128310 entity
Predicate spouse P13 FINISHED
Object Julie Wilson E507558 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: Julie Wilson | Statement: [Mel Tormé, spouse, Julie Wilson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Julie Wilson
Context triple: [Mel Tormé, spouse, Julie Wilson]
  • A. Julie Wilson chosen
    Julie Wilson was an American cabaret singer and actress celebrated for her sophisticated interpretations of the Great American Songbook and torch songs.
  • B. Julie Buck
    Julie Buck is a member of the Buck family, known primarily as a relative of American sportscaster Joe Buck.
  • C. Julie Gillis
    Julie Gillis is the charming, commitment-wary nightclub agent at the center of the 1955 romantic comedy film "The Tender Trap," whose bachelor lifestyle is upended by unexpected love.
  • D. Julie Powell
    Julie Powell was an American writer and blogger best known for her memoir "Julie & Julia," which chronicled her year-long project of cooking every recipe in Julia Child’s "Mastering the Art of French Cooking."
  • E. Julie Alexander
    Julie Alexander is an American businesswoman and former wife of legendary television and radio host Larry King.
  • 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_69c0084450048190bc647b649a05136b completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c02a5297c88190bd28adb2552a26f4 completed March 22, 2026, 5:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0981a002c8190ac8ed7407a80919c completed March 23, 2026, 1:32 a.m.
Created at: March 22, 2026, 3:51 p.m.