Triple

T4336490
Position Surface form Disambiguated ID Type / Status
Subject Angkor Archaeological Park E97474 entity
Predicate contains P35 FINISHED
Object Pre Rup E431204 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: Pre Rup | Statement: [Angkor Archaeological Park, contains, Pre Rup]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pre Rup
Context triple: [Angkor Archaeological Park, contains, Pre Rup]
  • A. Pre Rup chosen
    Pre Rup is a 10th-century Hindu temple mountain in Angkor, Cambodia, renowned for its brick and laterite construction and alignment with state ceremonies of the Khmer Empire.
  • B. Kamar-Taj
    Kamar-Taj is a hidden mystical sanctuary and training ground for sorcerers in the Marvel universe, where masters of the mystic arts teach magic and defend reality from supernatural threats.
  • C. Chamundi Hill
    Chamundi Hill is a prominent hill and pilgrimage site overlooking Mysuru, known for its ancient Chamundeshwari Temple and panoramic views of the city.
  • D. Parang
    Parang is a coastal town in the Philippines that served as a key Allied landing area during the World War II campaign to liberate Mindanao.
  • E. Elora Danan
    Elora Danan is the prophesied infant princess from the fantasy film "Willow," destined to bring about the downfall of the evil Queen Bavmorda.
  • 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_69b3454662a481908fbcd0bbfaa3a0a4 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b3516af43081908393fd0dad3d9382 completed March 12, 2026, 11:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5db9fd4988190afa9e04b029cd573 completed March 14, 2026, 10:05 p.m.
Created at: March 12, 2026, 11:14 p.m.