Triple

T10006182
Position Surface form Disambiguated ID Type / Status
Subject William Mills (British politician) E198248 entity
Predicate familyName P18 FINISHED
Object Mills E39389 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: Mills | Statement: [William Mills (British politician), familyName, Mills]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mills
Context triple: [William Mills (British politician), familyName, Mills]
  • A. Mills chosen
    Mills is a common English surname borne by numerous notable individuals across fields such as music, politics, sports, and academia.
  • B. The Mills
    The Mills is a portfolio of large outlet and value-oriented shopping malls in the United States, known for combining retail, dining, and entertainment under the ownership of Simon Property Group.
  • C. MILLom
    MILLom is a small coastal town in Cumbria, England, historically known for its ironworks and situated near the Duddon Estuary.
  • D. Milles
    Milles is a surname and variant of "Mills" that appears in English-speaking contexts.
  • E. The Mill
    "The Mill" is a dark, psychologically intense narrative poem by Edwin Arlington Robinson that explores themes of despair, miscommunication, and tragic misunderstanding within a miller’s family.
  • 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_69ca830fcca48190bbbd9b20c233835f completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cdcd16afb481909a5d5893e024683f completed April 2, 2026, 1:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69d26a5d7e088190b5b1a852bfdc9073 completed April 5, 2026, 1:57 p.m.
Created at: March 30, 2026, 8:51 p.m.