Triple

T14438613
Position Surface form Disambiguated ID Type / Status
Subject Bran Castle E358031 entity
Predicate locatedIn P40 FINISHED
Object Bran E895646 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: Bran | Statement: [Bran Castle, locatedIn, Bran]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bran
Context triple: [Bran Castle, locatedIn, Bran]
  • A. Bran
    Bran is a common diminutive form of the given name Brandon, often used as a short, familiar nickname.
  • B. Bran chosen
    Bran is a Romanian commune best known for Bran Castle, a medieval fortress often associated with the Dracula legend and a major tourist attraction in Transylvania.
  • C. Bran the Builder
    Bran the Builder is a legendary figure from Westerosi lore, famed as an ancient Stark ancestor credited with constructing monumental works such as the Wall and Winterfell.
  • D. Broten
    Broten is a surname most notably associated with American ice hockey player Neal Broten, a Stanley Cup champion and Olympic gold medalist.
  • E. Balnibarbi
    Balnibarbi is a fictional country in Jonathan Swift's satirical novel "Gulliver's Travels," known for its absurd scientific experiments and mismanaged society.
  • 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_69d8279402a88190821ffa39ae15bccf completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de914a45ec81909ab8ccf302047d7f completed April 14, 2026, 7:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd5bd7f46881908df1a1cea7b6af9b completed May 8, 2026, 3:43 a.m.
Created at: April 10, 2026, 1:18 a.m.