Triple

T15424553
Position Surface form Disambiguated ID Type / Status
Subject Max Dennison E369472 entity
Predicate familyName P18 FINISHED
Object Dennison E604871 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: Dennison | Statement: [Max Dennison, familyName, Dennison]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dennison
Context triple: [Max Dennison, familyName, Dennison]
  • A. Dennison chosen
    Dennison is the middle name of William Stephens, used as part of his full personal name.
  • B. Dennison, Ohio
    Dennison, Ohio is a small village in eastern Ohio historically known as a key railroad hub and World War II canteen stop for troop trains.
  • C. Denniston
    Denniston is a historic former coal-mining town on New Zealand’s rugged West Coast, known for its dramatic plateau setting and the famous Denniston Incline.
  • D. Oreston
    Oreston is a suburban district of Plymouth in Devon, England, known for its riverside location and maritime character.
  • E. Alanson
    Alanson is a small village in northern Michigan known for its location along the Crooked River and its access to the Inland Waterway.
  • 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_69d85a1849f48190bf898068b2806fae completed April 10, 2026, 2:02 a.m.
NER Named-entity recognition batch_69e03ec032548190840b558dde6057c7 completed April 16, 2026, 1:43 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff1a7ed0ec8190b8086f78df965b61 completed May 9, 2026, 11:29 a.m.
Created at: April 10, 2026, 3:20 a.m.