Triple

T10288515
Position Surface form Disambiguated ID Type / Status
Subject Martha Coakley E241298 entity
Predicate mainOpponent P437 FINISHED
Object Scott Brown E11570 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: Scott Brown | Statement: [Martha Coakley, mainOpponent, Scott Brown]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Scott Brown
Context triple: [Martha Coakley, mainOpponent, Scott Brown]
  • A. Scott Brown chosen
    Scott Brown is an American Republican politician and former U.S. Senator from Massachusetts who later served as U.S. Ambassador to New Zealand and Samoa.
  • B. Mark Raymond Harrington
    Mark Raymond Harrington was an American archaeologist and ethnologist known for his early 20th-century excavations and research on Indigenous cultures of the American West.
  • C. James McCain
    James McCain is one of the children of the late U.S. Senator and 2008 Republican presidential nominee John McCain.
  • D. Kerry
    Kerry is a given name used for people of any gender in English-speaking countries.
  • E. Kerry
    Kerry is a county in the southwest of Ireland known for its rugged coastline, mountains, and popular tourist destinations like Killarney and the Ring of Kerry.
  • 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_69d381aaafc08190af475ef58dc16aba completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d2b9d76c8190b1ef6ecf4c1a2a09 completed April 7, 2026, 9:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69d6f8556f4081908390bc5c14dcf560 completed April 9, 2026, 12:52 a.m.
Created at: April 6, 2026, 11:41 a.m.