Triple

T20891609
Position Surface form Disambiguated ID Type / Status
Subject William Maharg E514420 entity
Predicate familyName P18 FINISHED
Object Maharg NE NERFINISHED

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: Maharg | Statement: [William Maharg, familyName, Maharg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maharg
Context triple: [William Maharg, familyName, Maharg]
  • A. Maharg chosen
    Maharg is a surname most notably associated with Billy Maharg, an early 20th-century American baseball player and occasional boxing fixer.
  • B. Maasin
    Maasin is a coastal city in the Philippines that serves as the administrative, economic, and religious center of the province of Southern Leyte.
  • C. Marassi
    Marassi is a residential district of Genoa, Italy, best known for hosting the historic Stadio Luigi Ferraris football stadium.
  • D. Milna
    Milna is a picturesque coastal village and harbor town on the western side of the Croatian island of Brač, known for its traditional stone architecture and sheltered bay.
  • E. Milna
    Milna is a volcanic feature located on Simushir Island in Russia’s Kuril Islands chain.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4f7ebe48190952a85547a0f31a1 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6d05e307081908f1d044e877017ec completed April 21, 2026, 1:18 a.m.
Created at: April 16, 2026, 12:46 p.m.