Triple

T10278262
Position Surface form Disambiguated ID Type / Status
Subject Fort Scammel E241024 entity
Predicate locatedOn P40 FINISHED
Object House Island E241024 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: House Island | Statement: [Fort Scammel, locatedOn, House Island]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: House Island
Context triple: [Fort Scammel, locatedOn, House Island]
  • A. House Island chosen
    House Island is a small, privately owned island in Casco Bay, Maine, known for its historic Fort Scammel and scenic coastal views.
  • B. Tree Island
    Tree Island is a small disputed island in the South China Sea that forms part of the Paracel Islands archipelago.
  • C. Nut Island
    Nut Island is a small island in Boston Harbor known for its wastewater treatment facilities and recreational access as part of the Boston Harbor Islands.
  • D. Edge Island
    Edge Island is a large, remote island in the Svalbard archipelago of Arctic Norway, known for its polar wildlife and harsh glacial landscapes.
  • E. Low Island
    Low Island is a largely ice-covered, low-lying island located off the Antarctic Peninsula within the South Shetland Islands archipelago.
  • 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_69d381a94c1881908fc38fc263d9b9c2 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d29f0cf08190a2c5e7523d5c731e completed April 7, 2026, 9:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69dff74d59f88190bbd975521b16ae49 completed April 15, 2026, 8:38 p.m.
Created at: April 6, 2026, 11:38 a.m.