Triple

T11957240
Position Surface form Disambiguated ID Type / Status
Subject GLX E284583 entity
Predicate relatedTo P37 FINISHED
Object WGL E900032 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: WGL | Statement: [GLX, relatedTo, WGL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: WGL
Context triple: [GLX, relatedTo, WGL]
  • A. WGL
    WGL is the common abbreviation for the Leibniz Association, a major German network of non-university research institutes spanning a wide range of scientific disciplines.
  • B. WGL chosen
    WGL is an acronym that can refer to various organizations and concepts, most commonly Washington Gas Light Company, a natural gas utility serving the Washington, D.C. metropolitan area.
  • C. WOGL
    WOGL is a Philadelphia-based FM radio station known for its classic hits format and long-standing presence in the local broadcast market.
  • D. GWL
    GWL is the IATA airport code for Gwalior Airport, serving the city of Gwalior in the Indian state of Madhya Pradesh.
  • E. GWL
    GWL is the station code for Gwalior Junction, a major railway hub in the Indian state of Madhya Pradesh.
  • 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_69d6ab2db38c8190b1f0ed6663ef8ada completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d903681a00819098c2b5260e2ef834 completed April 10, 2026, 2:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69f459210d1c8190953cd01da3d2ad04 completed May 1, 2026, 7:41 a.m.
Created at: April 8, 2026, 9:45 p.m.