Triple

T15738873
Position Surface form Disambiguated ID Type / Status
Subject Varuna E381549 entity
Predicate mount P18930 FINISHED
Object makara E448849 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: makara | Statement: [Varuna, mount, makara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: makara
Context triple: [Varuna, mount, makara]
  • A. makara chosen
    Makara is a mythical sea creature in Hindu and Buddhist traditions, often depicted as a composite aquatic beast and used as a vehicle or emblem of water deities.
  • B. MaK
    MaK is a German engineering and manufacturing company historically known for producing heavy machinery, locomotives, and military vehicles.
  • C. Makadara
    Makadara is a residential and commercial neighborhood in Nairobi, Kenya, known for its dense population, vibrant local markets, and mix of low- to middle-income housing.
  • D. Mararaba
    Mararaba is a rapidly growing suburban town near Abuja in central Nigeria, known for its dense population and heavy commuter traffic.
  • E. Sukari
    "Sukari" is a popular Tanzanian Bongo Flava song by singer Zuchu that gained widespread acclaim across East Africa.
  • 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_69d86d9cdb648190bf3171be0bd7d872 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04fd816308190a297986ee7e5554c completed April 16, 2026, 2:56 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff830336248190a8bbd8153dd95daa completed May 9, 2026, 6:54 p.m.
Created at: April 10, 2026, 4:46 a.m.