Triple

T7476271
Position Surface form Disambiguated ID Type / Status
Subject McCullen v. Coakley E176639 entity
Predicate respondent P2238 FINISHED
Object Martha Coakley E241298 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: Martha Coakley | Statement: [McCullen v. Coakley, respondent, Martha Coakley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Martha Coakley
Context triple: [McCullen v. Coakley, respondent, Martha Coakley]
  • A. Martha Coakley chosen
    Martha Coakley is an American lawyer and politician who served as Attorney General of Massachusetts and was the Democratic nominee in the state's 2010 U.S. Senate and 2014 gubernatorial races.
  • B. Maura Healey
    Maura Healey is an American politician and attorney who became the first woman and first openly lesbian governor of Massachusetts.
  • C. Jean Saltonstall
    Jean Saltonstall was a member of a prominent Boston Brahmin family and the first wife of journalist and longtime Washington Post executive editor Ben Bradlee.
  • D. Katherine Corri Harris
    Katherine Corri Harris was an American stage and silent film actress best known as the first wife of famed actor John Barrymore.
  • E. Gail C. Murphy
    Gail C. Murphy is a prominent Canadian computer scientist known for her influential research in software engineering, particularly in improving developer productivity and software evolution.
  • 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_69c69f236ce08190a04d7679f03b29b2 completed March 27, 2026, 3:15 p.m.
NER Named-entity recognition batch_69c6f4ee23d081908e05658a651661fc completed March 27, 2026, 9:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69c83489a8208190b0380edcd18a1246 completed March 28, 2026, 8:05 p.m.
Created at: March 27, 2026, 3:41 p.m.