Triple

T21551048
Position Surface form Disambiguated ID Type / Status
Subject East Devon E531760 entity
Predicate hasRiver P165 FINISHED
Object River Axe 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: River Axe | Statement: [East Devon, hasRiver, River Axe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: River Axe
Context triple: [East Devon, hasRiver, River Axe]
  • A. River Axe chosen
    The River Axe is a river in southwest England that flows through Somerset and Dorset before reaching the English Channel.
  • B. The Ax
    The Ax is a darkly comic crime novel by Donald E. Westlake about a downsized executive who turns to murder to eliminate his job-market rivals.
  • C. The Axe
    The Axe is a novel by Sigrid Undset that forms part of her medieval Norwegian saga cycle "The Master of Hestviken."
  • D. The Spear
    The Spear is the nickname of the U.S. Air Force’s 53rd Wing, a unit known for operational testing and evaluation of advanced weapons and systems.
  • E. The Axe-Helve
    "The Axe-Helve" is a narrative poem by Robert Frost that explores themes of craftsmanship, cultural difference, and human connection through a neighborly encounter over a woodcutting tool.
  • 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_69e0c460232c81908de2c3819d17c00e completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69eeb59258b88190966c18f1f519dad6 completed April 27, 2026, 1:02 a.m.
Created at: April 16, 2026, 6:29 p.m.