Triple

T14952158
Position Surface form Disambiguated ID Type / Status
Subject Hastings Castle E372821 entity
Predicate locatedIn P40 FINISHED
Object Hastings E75945 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: Hastings | Statement: [Hastings Castle, locatedIn, Hastings]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hastings
Context triple: [Hastings Castle, locatedIn, Hastings]
  • A. Hastings chosen
    Hastings is a historic seaside town and popular coastal resort in East Sussex, England, best known for its association with the 1066 Battle of Hastings and its traditional fishing and tourism industries.
  • B. Hastings
    Hastings is a major urban center in the Hawke's Bay region of New Zealand's North Island, known for its agriculture, wineries, and Art Deco and Spanish Mission-style architecture.
  • C. Hastings
    Hastings is a surname most prominently associated with Reed Hastings, the co-founder and longtime CEO of Netflix.
  • D. Hastings
    Hastings is a coastal town on Victoria, Australia’s Mornington Peninsula known for its port facilities and access to Western Port Bay.
  • E. Hastings
    Hastings is a small rural city located in Mills County in the southwestern part of the U.S. state of Iowa.
  • 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_69d85cca979481908747d2a81eba1cea completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded690f2e08190ad9dad6dc05a164a completed April 15, 2026, 12:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe968bbbac8190a258c42b226f9def completed May 9, 2026, 2:06 a.m.
Created at: April 10, 2026, 2:39 a.m.