Triple

T5084000
Position Surface form Disambiguated ID Type / Status
Subject Barnstaple E114590 entity
Predicate railwayLine P848 FINISHED
Object Tarka Line E166302 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: Tarka Line | Statement: [Barnstaple, railwayLine, Tarka Line]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tarka Line
Context triple: [Barnstaple, railwayLine, Tarka Line]
  • A. Tarka Line chosen
    The Tarka Line is a scenic rural railway route in Devon, England, running between Exeter and Barnstaple through the countryside associated with Henry Williamson’s novel "Tarka the Otter."
  • B. Butovskaya Line
    The Butovskaya Line is a light metro line in the Moscow Metro system serving the Butovo district in the city’s south.
  • C. Batong Line
    The Batong Line is a rapid transit line in Beijing that extends the Beijing Subway network eastward into the suburban Tongzhou District.
  • D. Saburtalo Line
    The Saburtalo Line is one of the main rapid transit lines of the Tbilisi Metro system in Tbilisi, Georgia, serving several central and residential districts of the city.
  • E. Winter Line
    The Winter Line was a series of German defensive fortifications in southern Italy during World War II, designed to delay the Allied advance toward Rome.
  • 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_69bd443e941881908eb4e8c685b6f656 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd7517af308190bab5507a9344bf68 completed March 20, 2026, 4:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69beb135912c81909dd32d21b604e1b1 completed March 21, 2026, 2:54 p.m.
Created at: March 20, 2026, 1:40 p.m.