Triple

T13918598
Position Surface form Disambiguated ID Type / Status
Subject Tengri E334683 entity
Predicate relatedDeity P23286 FINISHED
Object Erlik E336892 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: Erlik | Statement: [Tengri, relatedDeity, Erlik]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Erlik
Context triple: [Tengri, relatedDeity, Erlik]
  • A. Erlik chosen
    Erlik is the god of death and the underworld in Turkic and Mongolic mythology, often portrayed as a powerful and fearsome ruler of the dead.
  • B. Larak
    Larak was an ancient Sumerian city-state, known primarily from the Sumerian King List as an early center of kingship in Mesopotamia.
  • C. Ekeremor
    Ekeremor is a local government area in Nigeria’s oil-rich Niger Delta region, known for its riverine communities and location within Bayelsa State.
  • D. Akhras
    Akhras is a Syrian-origin family name best known for being the maiden surname of Asma al-Assad, the First Lady of Syria.
  • E. Kishar
    Kishar is a primordial Mesopotamian earth goddess associated with the horizon and paired with the sky god Anshar in ancient creation myths.
  • 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_69d81c5f739081908bc05b2461f54828 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de272753e48190bc609482635280ff completed April 14, 2026, 11:38 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7ce7a1c388190a57dfdbbb732bbcb completed May 3, 2026, 10:38 p.m.
Created at: April 9, 2026, 10:16 p.m.