Triple

T23428478
Position Surface form Disambiguated ID Type / Status
Subject Sajik-dong E563258 entity
Predicate nearbyHistoricSite P19575 FINISHED
Object Sajikdan altar 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: Sajikdan altar | Statement: [Sajik-dong, nearbyHistoricSite, Sajikdan altar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sajikdan altar
Context triple: [Sajik-dong, nearbyHistoricSite, Sajikdan altar]
  • A. Sajikdan altar chosen
    Sajikdan altar is a historic state altar in Seoul, South Korea, where Joseon dynasty rulers performed important national rites to the deities of earth and grain.
  • B. Stone Shrine
    Stone Shrine is the English meaning of "Gal Vihara," the name of a renowned ancient rock temple in Polonnaruwa, Sri Lanka, famous for its large Buddha statues carved into a granite cliff.
  • C. Sajibu
    Sajibu is the first month of the traditional Meitei lunar calendar, marking the beginning of the new year in Manipur.
  • D. The Altar
    The Altar is a metaphysical devotional poem by George Herbert that uses a shaped, emblematic layout to express the speaker’s heart as a sacrificial altar dedicated to God.
  • E. The Altar
    The Altar is a prominent stratovolcano in Ecuador’s Andes, known for its dramatic eroded crater and multiple snow-capped peaks.
  • 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_69e24553980c8190bb66a2ae0bdab125 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f1a54ba29881909945690496f28d65 completed April 29, 2026, 6:29 a.m.
Created at: April 17, 2026, 5:48 p.m.