Triple

T10329951
Position Surface form Disambiguated ID Type / Status
Subject Geography Markup Language E242848 entity
Predicate earlierVersion P22508 FINISHED
Object GML 2 E48510 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: GML 2 | Statement: [Geography Markup Language, earlierVersion, GML 2]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: GML 2
Context triple: [Geography Markup Language, earlierVersion, GML 2]
  • A. GML chosen
    GML (Geography Markup Language) is an XML-based standard developed by the Open Geospatial Consortium for modeling, transporting, and storing geographic information and spatial features.
  • B. GD 2
    GD 2 is a designated paleontological and archaeological site within Gondolin Cave in South Africa, known for its fossil-bearing deposits.
  • C. Terminal 2G
    Terminal 2G is a regional satellite terminal at Paris Charles de Gaulle Airport primarily serving short-haul European flights operated by Air France and its partners.
  • D. Gemin2
    Gemin2 is a core component of the SMN complex that plays a crucial role in the assembly of small nuclear ribonucleoproteins (snRNPs) essential for pre-mRNA splicing.
  • E. G2X
    G2X is a compact sports car model produced by Daewoo (also known as the Daewoo G2X), recognized for its sleek design and performance-oriented features.
  • 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_69d381af787481908bc401325c760a88 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d7fb77348190ac8ff887f6f03450 completed April 7, 2026, 10:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69d71dbc7df48190b8a11a92f946fd30 completed April 9, 2026, 3:32 a.m.
Created at: April 6, 2026, 11:52 a.m.