Triple

T7514208
Position Surface form Disambiguated ID Type / Status
Subject Yerebatan Sarnıcı E177598 entity
Predicate alsoKnownAs P39 FINISHED
Object Sunken Cistern E177598 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: Sunken Cistern | Statement: [Yerebatan Sarnıcı, alsoKnownAs, Sunken Cistern]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sunken Cistern
Context triple: [Yerebatan Sarnıcı, alsoKnownAs, Sunken Cistern]
  • A. Etruscan Well
    The Etruscan Well is an ancient underground water cistern in Perugia, Italy, notable for its impressive Etruscan engineering and stone construction dating back to the 3rd–4th century BCE.
  • B. Kallichoron Well
    Kallichoron Well is an ancient sacred well at Eleusis in Greece, closely associated with the Eleusinian Mysteries and the myth of Demeter’s search for Persephone.
  • C. Roman Well
    Roman Well is a historic underground water reservoir and tourist attraction located within Belgrade Fortress in Belgrade, Serbia.
  • D. Yerebatan Sarnıcı chosen
    Yerebatan Sarnıcı is a vast underground Byzantine cistern in Istanbul, famed for its forest of marble columns and atmospheric, water-filled interior.
  • E. Nun’s Well
    Nun’s Well is a historic underground water cistern at Gibraltar’s Europa Point, traditionally used as a key freshwater source for the area.
  • 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_69c69f2891148190a484f3b8222c6f1b completed March 27, 2026, 3:15 p.m.
NER Named-entity recognition batch_69c6f5d6ccb08190a568a9b58bfbd0cc completed March 27, 2026, 9:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69c84619aac8819083a1d7380f4b30d3 completed March 28, 2026, 9:20 p.m.
Created at: March 27, 2026, 3:45 p.m.