Triple

T12933658
Position Surface form Disambiguated ID Type / Status
Subject Battle of Gela E309447 entity
Predicate location P40 FINISHED
Object Gela, Sicily E55087 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: Gela, Sicily | Statement: [Battle of Gela, location, Gela, Sicily]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gela, Sicily
Context triple: [Battle of Gela, location, Gela, Sicily]
  • A. Gela
    Gela is an Oceanic language spoken primarily in the Solomon Islands, particularly on Nggela (Florida) Islands in Central Province.
  • B. Gela
    Gela is a river in southern Sicily, Italy, that flows into the Mediterranean Sea near the city of Gela.
  • C. Gela
    Gela is a mountain village in the Rhodope Mountains of southern Bulgaria, known for its scenic landscapes and traditional Bulgarian culture.
  • D. Gela chosen
    Gela is an ancient Greek colonial city on the southern coast of Sicily that was a significant center of Magna Graecia.
  • E. Syracuse, Sicily
    Syracuse, Sicily is a historic coastal city on the southeastern coast of the Italian island of Sicily, renowned for its ancient Greek and Roman ruins and its role as a major power in classical antiquity.
  • 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_69d7bdfa933c8190b5a27aa4a08a19b7 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d97dc6517481908637781da240b51f completed April 10, 2026, 10:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcdee8d1408190942ff455e7b1b6e2 completed May 7, 2026, 6:50 p.m.
Created at: April 9, 2026, 5:42 p.m.