Triple

T14952434
Position Surface form Disambiguated ID Type / Status
Subject Oirat people E372827 entity
Predicate writingSystem P454 FINISHED
Object Clear Script E300217 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: Clear Script | Statement: [Oirat people, writingSystem, Clear Script]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Clear Script
Context triple: [Oirat people, writingSystem, Clear Script]
  • A. Clear script (Todo script) chosen
    Clear script (Todo script) is a vertically written alphabetic script developed in the 17th century for writing Mongolic languages, particularly among the Oirat Mongols.
  • B. Interface Clear
    Interface Clear is a company specializing in building automation and control systems, particularly focused on integrating and managing HVAC and related building technologies.
  • C. St Clears
    St Clears is a small town and community in Carmarthenshire, Wales, known for its historic abbey remains and position near the River Taf.
  • D. Clearing
    Clearing is a residential and industrial neighborhood on the southwest side of Chicago, known for encompassing and surrounding Midway International Airport.
  • E. Clearing
    "Clearing" is a large-scale photographic work by German artist Thomas Demand, known for its meticulously constructed paper model of a forest scene that blurs the line between reality and fabrication.
  • 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_69d85cca979481908747d2a81eba1cea completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded690f2e08190ad9dad6dc05a164a completed April 15, 2026, 12:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe7e9a6098819087b6e81bebcf6805 completed May 9, 2026, 12:23 a.m.
Created at: April 10, 2026, 2:39 a.m.