Triple

T11460830
Position Surface form Disambiguated ID Type / Status
Subject White Mountains E271653 entity
Predicate notableLocation P3858 FINISHED
Object Hornburg E820187 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: Hornburg | Statement: [White Mountains, notableLocation, Hornburg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hornburg
Context triple: [White Mountains, notableLocation, Hornburg]
  • A. Hornburg chosen
    Hornburg is the fortified stronghold of Rohan in J.R.R. Tolkien's Middle-earth, built against the cliffs of the White Mountains and guarding the strategic refuge of Helm's Deep.
  • B. Hordern
    Hordern is an English surname most notably associated with the distinguished British actor Sir Michael Hordern.
  • C. Hornburg tower
    The Hornburg tower is a fortified stronghold of Rohan in J.R.R. Tolkien's Middle-earth, serving as the central keep of the fortress at Helm's Deep.
  • D. Hinton Parva
    Hinton Parva is a small rural village in Wiltshire, England, known for its historic character and scenic countryside setting.
  • E. Hallerowo
    Hallerowo is a district of the seaside town Władysławowo in northern Poland, known for its coastal location on the Baltic Sea.
  • 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_69d6aadff8888190a13f253f0d460874 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d822f384f08190b1150ed1389dd31a completed April 9, 2026, 10:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69e5e91f1bb881909a9c36d837e4059b completed April 20, 2026, 8:51 a.m.
Created at: April 8, 2026, 9:35 p.m.