Triple

T14513635
Position Surface form Disambiguated ID Type / Status
Subject Catelyn Stark E340461 entity
Predicate origin P410 FINISHED
Object Riverrun E345010 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: Riverrun | Statement: [Catelyn Stark, origin, Riverrun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Riverrun
Context triple: [Catelyn Stark, origin, Riverrun]
  • A. Riverrun chosen
    Riverrun is the ancestral castle and stronghold of House Tully, strategically located at the confluence of rivers in the Riverlands of Westeros in George R.R. Martin’s A Song of Ice and Fire series.
  • B. Faulconbridge
    Faulconbridge is a village in the Blue Mountains region of New South Wales, Australia, known for its bushland setting and historic association with Australian prime minister Sir Henry Parkes.
  • C. Darnhall
    Darnhall is a rural village and civil parish in Cheshire, England, known for its agricultural landscape and historic ties to the medieval Darnhall Abbey.
  • D. Avonbridge
    Avonbridge is a small rural village in central Scotland situated between Falkirk and West Lothian.
  • E. Ravensworth
    Ravensworth is a rural locality within Singleton Shire in New South Wales, Australia, known for its agricultural lands and proximity to mining operations.
  • 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_69d822d9c0408190b9a2b3643e58bb4d completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69de9a6d82988190b6f957012bcc63d4 completed April 14, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd7a49484081908fd2030d33727a6d completed May 8, 2026, 5:53 a.m.
Created at: April 10, 2026, 1:21 a.m.