Triple

T10865759
Position Surface form Disambiguated ID Type / Status
Subject Farne Islands E256524 entity
Predicate hasIsland P970 FINISHED
Object Big Harcar
Big Harcar is one of the rocky Farne Islands off the coast of Northumberland, England, known for its seabird colonies and treacherous surrounding waters.
E891349 NE FINISHED

How this triple was built (4 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: Big Harcar | Statement: [Farne Islands, hasIsland, Big Harcar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Big Harcar
Context triple: [Farne Islands, hasIsland, Big Harcar]
  • A. Parlick
    Parlick is a prominent hill in Lancashire, England, popular with walkers and paragliders and known for its sweeping views over the Forest of Bowland.
  • B. Haro
    Haro is a historic town in Spain’s La Rioja region, renowned for its wineries and annual wine festival.
  • C. Big Eagle
    Big Eagle was a prominent Mdewakanton Dakota leader known for his key role in the Dakota War of 1862 against United States forces in Minnesota.
  • D. Milhous
    Milhous is the distinctive middle name of Richard Nixon, the 37th president of the United States.
  • E. Harbison
    Harbison is a surname most notably associated with American composer John Harbison, known for his contributions to contemporary classical music.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Big Harcar
Triple: [Farne Islands, hasIsland, Big Harcar]
Generated description
Big Harcar is one of the rocky Farne Islands off the coast of Northumberland, England, known for its seabird colonies and treacherous surrounding waters.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Big Harcar
Target entity description: Big Harcar is one of the rocky Farne Islands off the coast of Northumberland, England, known for its seabird colonies and treacherous surrounding waters.
  • A. Parlick
    Parlick is a prominent hill in Lancashire, England, popular with walkers and paragliders and known for its sweeping views over the Forest of Bowland.
  • B. Haro
    Haro is a historic town in Spain’s La Rioja region, renowned for its wineries and annual wine festival.
  • C. Big Eagle
    Big Eagle was a prominent Mdewakanton Dakota leader known for his key role in the Dakota War of 1862 against United States forces in Minnesota.
  • D. Milhous
    Milhous is the distinctive middle name of Richard Nixon, the 37th president of the United States.
  • E. Harbison
    Harbison is a surname most notably associated with American composer John Harbison, known for his contributions to contemporary classical music.
  • F. None of above. chosen

Provenance (5 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_69d6aa83d1448190a66d93c32394d21f completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d7516cebe881909ed358a7641f6a12 completed April 9, 2026, 7:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69dff7d7b32081909dd5f8ae3fe293be completed April 15, 2026, 8:40 p.m.
NEDg Description generation batch_69e0b498df2481908c964d53b1782774 completed April 16, 2026, 10:06 a.m.
NED2 Entity disambiguation (via description) batch_69e11e21fc2c8190878a877ecd3b465e completed April 16, 2026, 5:36 p.m.
Created at: April 8, 2026, 9:20 p.m.