Triple

T23396221
Position Surface form Disambiguated ID Type / Status
Subject Earls of Mar E559366 entity
Predicate region P40 FINISHED
Object Mar 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: Mar | Statement: [Earls of Mar, region, Mar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mar
Context triple: [Earls of Mar, region, Mar]
  • A. Mar
    Mar is an honorific ecclesiastical title used for bishops and saints in several Eastern Christian traditions, particularly within Syriac Christianity.
  • B. Mar chosen
    Mar is a historic earldom and region in Aberdeenshire, Scotland, long associated with one of the oldest Scottish peerage titles, the Earldom of Mar.
  • C. MA
    MA is the IATA airline designator formerly assigned to Malév Hungarian Airlines, the former flag carrier of Hungary.
  • D. MA
    MA is the vehicle registration code used on license plates for the German city of Mannheim.
  • E. MA
    MA is the commonly used abbreviation for the Supreme Court of Indonesia, the country's highest judicial authority.
  • 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_69e24549610c8190a069d6411ce5f661 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1a4dc48008190bdcf92f8d9a5232d completed April 29, 2026, 6:27 a.m.
Created at: April 17, 2026, 5:36 p.m.