Triple

T17356685
Position Surface form Disambiguated ID Type / Status
Subject Bagan temples E421953 entity
Predicate notableTemple P13905 FINISHED
Object Sulamani Temple 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: Sulamani Temple | Statement: [Bagan temples, notableTemple, Sulamani Temple]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sulamani Temple
Context triple: [Bagan temples, notableTemple, Sulamani Temple]
  • A. Sulamani Temple chosen
    Sulamani Temple is a grand 12th-century Buddhist temple in Bagan, Myanmar, renowned for its elegant brick architecture and well-preserved interior frescoes.
  • B. Barran Temple
    Barran Temple is an ancient Sabaean religious complex in present-day Yemen, renowned as one of the most important pre-Islamic temples of South Arabia.
  • C. Indrunag Temple
    Indrunag Temple is a Hindu shrine located in Himachal Pradesh’s Kangra district, known for its hilltop setting and scenic views of the surrounding valleys.
  • D. Temple of Amada
    The Temple of Amada is an ancient Egyptian temple in Nubia, renowned as one of the region’s oldest surviving temples and noted for its finely preserved reliefs and inscriptions.
  • E. Aplan temple
    The Aplan temple is an ancient subterranean structure on the planet Alfava Metraxis, notable as the site of a deadly encounter with the Weeping Angels in the Doctor Who universe.
  • 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_69d889d520008190a26917a95bf1c2ea completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43a4976788190b00c00f710be6c46 completed April 19, 2026, 2:13 a.m.
Created at: April 10, 2026, 5:44 a.m.