Triple

T19782543
Position Surface form Disambiguated ID Type / Status
Subject Manu Temple E475173 entity
Predicate dedicatedTo P500 FINISHED
Object sage Manu 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: sage Manu | Statement: [Manu Temple, dedicatedTo, sage Manu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: sage Manu
Context triple: [Manu Temple, dedicatedTo, sage Manu]
  • A. Sage Manu chosen
    Sage Manu is the legendary Hindu lawgiver and progenitor of mankind, traditionally regarded as the author of the ancient legal and ethical text Manusmriti.
  • B. Sage
    Sage is a translucent, greenish color variant used on certain models of Apple's iMac G3 computers.
  • C. Sage
    Sage is a surname most notably associated with American actress Halston Sage, known for her roles in film and television.
  • D. MANU
    MANU is the acronym for the Macedonian Academy of Sciences and Arts, the leading national institution for scientific and artistic research in North Macedonia.
  • E. Simanu
    Simanu is a month in the ancient Babylonian calendar, corresponding roughly to late spring or early summer in the modern Gregorian calendar.
  • 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_69d8e51b014081908b263e167370529a completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e653852e848190b8971981a164e8f9 completed April 20, 2026, 4:25 p.m.
Created at: April 10, 2026, 1:49 p.m.