Triple

T17939898
Position Surface form Disambiguated ID Type / Status
Subject Tirumala Hills E448558 entity
Predicate hasDeity P5606 FINISHED
Object Srinivasa NE NERFINISHED

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: Srinivasa | Statement: [Tirumala Hills, hasDeity, Srinivasa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Srinivasa
Context triple: [Tirumala Hills, hasDeity, Srinivasa]
  • A. Srinivasa Ramanujan
    Srinivasa Ramanujan was an Indian mathematical prodigy whose groundbreaking, largely self-taught contributions to number theory, infinite series, and continued fractions profoundly influenced modern mathematics.
  • B. S. Srinivasa Iyengar
    S. Srinivasa Iyengar was a prominent Indian lawyer, nationalist leader, and politician who played a key role in the Indian independence movement and served as a leading figure in the Indian National Congress.
  • C. Madhava chosen
    Madhava is a revered epithet of the Hindu god Vishnu, highlighting him as the consort of Lakshmi and the supreme preserver of the universe.
  • D. Nīlakaṇṭha
    Nīlakaṇṭha is an epithet of the Hindu god Shiva, referring to him as the “blue-throated” one who drank poison to save the universe.
  • E. Sridhara
    Sridhara was a notable poet associated with the Rashtrakuta dynasty, known for composing works under the patronage of its royal court.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b9f79d14819095540856928f0e25 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4ad9533688190bff773c183ed8505 completed April 19, 2026, 10:25 a.m.
Created at: April 10, 2026, 10:21 a.m.