Triple

T15583793
Position Surface form Disambiguated ID Type / Status
Subject Temple of Bel E374566 entity
Predicate hasPart P35 FINISHED
Object propylaea E17510 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: propylaea | Statement: [Temple of Bel, hasPart, propylaea]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: propylaea
Context triple: [Temple of Bel, hasPart, propylaea]
  • A. Propylaea chosen
    Propylaea is the monumental classical gateway that serves as the grand entrance to the Acropolis in Athens.
  • B. Parailia
    Parailia is a genus of small African freshwater catfishes known for their slender, often translucent bodies and schooling behavior.
  • C. Prousos
    Prousos is a small mountainous village in central Greece, known for its historic monastery and scenic location in the region of Evrytania.
  • D. Potaissa
    Potaissa is the ancient Roman name of the modern city of Turda in present-day Romania, known historically as a significant military and administrative center in the province of Dacia.
  • E. Aspropyrgos
    Aspropyrgos is an industrial town in the western part of the Athens metropolitan area in Greece, known for its refineries and heavy industry.
  • 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_69d85ccd575081908909b71a3f3e3a61 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e47971481909e986dd999354628 completed April 16, 2026, 2:49 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff4c4f71e48190a15eb0a2138f083f completed May 9, 2026, 3:01 p.m.
Created at: April 10, 2026, 4:11 a.m.