Triple

T21981250
Position Surface form Disambiguated ID Type / Status
Subject Little Town E542844 entity
Predicate near P350 FINISHED
Object Robinson (fell) NE NERFINISHED

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: Robinson (fell) | Statement: [Little Town, near, Robinson (fell)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robinson (fell)
Context triple: [Little Town, near, Robinson (fell)]
  • A. Robbinsen
    Robbinsen is a surname variant of Robbins, likely sharing the same English patronymic origins derived from the given name Robin.
  • B. Rōben
    Rōben was an influential 8th-century Japanese Buddhist monk of the Kegon school, known for helping establish major temples such as Tōdai-ji and shaping early Nara Buddhism.
  • C. Robinson chosen
    Robinson is a common English surname borne by numerous notable figures across politics, sports, arts, and other fields.
  • D. Rompin
    Rompin is a town in Malaysia’s Negeri Sembilan state that serves as one of the main local centers of the Jempol District.
  • E. Cliff
    Cliff is a masculine given name, often used as a short form of Clifford or Clifton.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0c48136b081908831fa907cc02e18 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f1248de3688190a8d24cc8458851f2 completed April 28, 2026, 9:20 p.m.
Created at: April 16, 2026, 8:04 p.m.