Triple

T167633
Position Surface form Disambiguated ID Type / Status
Subject Boston campaign E3050 entity
Predicate commander P1061 FINISHED
Object Israel Putnam E14116 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: Israel Putnam | Statement: [Boston campaign, commander, Israel Putnam]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Israel Putnam
Context triple: [Boston campaign, commander, Israel Putnam]
  • A. Israel Putnam chosen
    Israel Putnam was a prominent American Revolutionary War general known for his leadership at the Battle of Bunker Hill and his role in the early Continental Army.
  • B. John Stark
    John Stark was an American Revolutionary War general from New Hampshire, best known for his leadership at the Battle of Bennington and for inspiring the state motto "Live Free or Die."
  • C. William Dawes
    William Dawes was an architect known for his work on major British railway stations, including the design of Manchester Victoria.
  • D. Myles Standish
    Myles Standish was an English military officer who served as the chief military leader and advisor for the Pilgrims in the early years of the Plymouth Colony in New England.
  • E. Thomas Gage
    Thomas Gage was a British Army general and colonial governor of Massachusetts whose policies and military actions helped spark the American Revolutionary War.
  • 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_69a2524ce1e48190ab066bf72859f474 completed Feb. 28, 2026, 2:26 a.m.
NER Named-entity recognition batch_69a258b58efc8190959c86f73d67b744 completed Feb. 28, 2026, 2:53 a.m.
NED1 Entity disambiguation (via context triple) batch_69a36475d2608190ac11703d8b5e8107 completed Feb. 28, 2026, 9:56 p.m.
Created at: Feb. 28, 2026, 2:34 a.m.