Triple

T15762100
Position Surface form Disambiguated ID Type / Status
Subject Port of Cork E382125 entity
Predicate locatedIn P40 FINISHED
Object Cork E301817 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: Cork | Statement: [Port of Cork, locatedIn, Cork]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cork
Context triple: [Port of Cork, locatedIn, Cork]
  • A. Cork chosen
    Cork is a major county in the south of Ireland, known for its vibrant cultural heritage, extensive coastline, and the city of Cork, one of the country’s largest urban centers.
  • B. Cork city
    Cork city is a major port and the second-largest city in the Republic of Ireland, known for its rich maritime history, vibrant cultural scene, and role as the commercial and administrative center of County Cork.
  • C. Galway
    Galway is a small rural town in Saratoga County, New York, known for its scenic countryside and close-knit community.
  • D. Galway
    Galway is a vibrant coastal city in western Ireland known for its rich cultural heritage, lively arts and music scene, and historic medieval streets.
  • E. Cobh
    Cobh is a picturesque coastal town and seaport in southern Ireland, historically known as a major transatlantic departure point and the last port of call of the RMS Titanic.
  • 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_69d86d9e6b44819085d1f6a969ecb74c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e050b52c548190a0ffa4493a4eb15c completed April 16, 2026, 3 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00a502c82881908d5b6f7c23e8a403 completed May 10, 2026, 3:32 p.m.
Created at: April 10, 2026, 4:47 a.m.