Triple

T9777815
Position Surface form Disambiguated ID Type / Status
Subject Narya E237289 entity
Predicate raceOfBearers P90609 FINISHED
Object Maia E237282 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: Maia | Statement: [Narya, raceOfBearers, Maia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maia
Context triple: [Narya, raceOfBearers, Maia]
  • A. Maia chosen
    Maia are powerful immortal spirits in J.R.R. Tolkien’s legendarium who serve the Valar and often act as guides or guardians to the peoples of Middle-earth.
  • B. Maia
    Maia is a figure from Greek mythology, one of the Pleiades and the mother of the god Hermes.
  • C. Maia
    Maia is a fantasy novel by Richard Adams set in the same world as his book "Shardik," following the adventures of a young slave girl in a richly detailed, politically complex empire.
  • D. Maia
    Maia is a common Portuguese surname borne by numerous notable figures in Portugal’s history and public life.
  • E. Maeva
    Maeva is a traditional lakeside village on the island of Huahine in French Polynesia, known for its well-preserved archaeological sites and ancient Polynesian marae.
  • 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_69ca84d975a08190aab25b02a89bdab3 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cda13545808190a47544b0cc666e20 completed April 1, 2026, 10:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1d5a8564081908b315d2cf68c8e14 completed April 5, 2026, 3:23 a.m.
Created at: March 30, 2026, 8:26 p.m.