Triple

T13892890
Position Surface form Disambiguated ID Type / Status
Subject Like a Virgin E334017 entity
Predicate composer P1361 FINISHED
Object Tom Kelly E512526 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: Tom Kelly | Statement: [Like a Virgin, composer, Tom Kelly]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tom Kelly
Context triple: [Like a Virgin, composer, Tom Kelly]
  • A. Tom Kelly
    Tom Kelly is a former Major League Baseball manager best known for leading the Minnesota Twins to two World Series championships in 1987 and 1991.
  • B. Tom Kelly chosen
    Tom Kelly is an American songwriter best known for co-writing numerous pop hits of the 1980s and 1990s, often in collaboration with Billy Steinberg.
  • C. Bill Kelly
    Bill Kelly is an American screenwriter best known for writing the fantasy romantic comedy film "Enchanted."
  • D. Gene Keady
    Gene Keady is a highly respected American college basketball coach best known for his long, successful tenure leading the Purdue Boilermakers.
  • E. Tommy Kelly
    Tommy Kelly was an American child actor best known for playing the title role in the 1938 film adaptation of "The Adventures of Tom Sawyer."
  • 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_69d81c5dd2d48190b7a5fc1e009de936 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de23a537d4819093c2bae2a244816a completed April 14, 2026, 11:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7c71ca8a881908ac02687fbfe62fb completed May 3, 2026, 10:07 p.m.
Created at: April 9, 2026, 10:15 p.m.