Triple

T19360621
Position Surface form Disambiguated ID Type / Status
Subject Sibylla of Conversano E484268 entity
Predicate placeOfOrigin P3743 FINISHED
Object Conversano 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: Conversano | Statement: [Sibylla of Conversano, placeOfOrigin, Conversano]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Conversano
Context triple: [Sibylla of Conversano, placeOfOrigin, Conversano]
  • A. Conversano chosen
    Conversano is a historic hilltop town in the Apulia region of southern Italy, known for its medieval castle, Romanesque cathedral, and traditional white-stone architecture.
  • B. Parla
    Parla is a suburban municipality and residential town located in the southern metropolitan area of Madrid, Spain.
  • C. Melfi
    Melfi is a historic town in southern Italy known as an important medieval center of Norman rule and site of several papal councils.
  • D. Bolognano
    Bolognano is a small Italian municipality in the Abruzzo region, known for its scenic setting near the Maiella mountains and its historic architecture.
  • E. Fasano
    Fasano is a historic town and popular tourist destination in the Apulia region of southern Italy, known for its whitewashed old center, nearby trulli houses, and coastal resorts.
  • 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_69d8e8d305088190ad13571532aa454c completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e6190c2a8081908f48dfa738248ec8 completed April 20, 2026, 12:16 p.m.
Created at: April 10, 2026, 1:34 p.m.