Triple

T12578829
Position Surface form Disambiguated ID Type / Status
Subject Lough Mask E300279 entity
Predicate locatedNear P294 FINISHED
Object Cong E981967 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: Cong | Statement: [Lough Mask, locatedNear, Cong]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cong
Context triple: [Lough Mask, locatedNear, Cong]
  • A. Cong chosen
    Cong is a picturesque village in County Mayo, Ireland, famed for its historic abbey, scenic lakeside setting between Lough Corrib and Lough Mask, and as a primary filming location for the classic movie "The Quiet Man."
  • B. Con
    Con is a common diminutive or nickname for the given name Conrad.
  • C. Contin
    Contin is a small village and historic parish in the Highland council area of Scotland, situated near the River Black Water and known as a gateway to the surrounding glens and lochs.
  • D. Coll
    Coll is a small, sparsely populated island in the Inner Hebrides of Scotland, known for its sandy beaches, dark skies, and rich wildlife.
  • E. Cor
    Cor is a common Dutch diminutive or short form of the given name Cornelis.
  • 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_69d7bde87b648190bcd0266e9efde098 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d954a73c148190bba8f16b1232fd46 completed April 10, 2026, 7:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69f65599a9c0819086233fb2c622d243 completed May 2, 2026, 7:50 p.m.
Created at: April 9, 2026, 4:58 p.m.