Triple

T21549393
Position Surface form Disambiguated ID Type / Status
Subject Basilica of San Francesco E531719 entity
Predicate municipality P852 FINISHED
Object Comune di Arezzo 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: Comune di Arezzo | Statement: [Basilica of San Francesco, municipality, Comune di Arezzo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Comune di Arezzo
Context triple: [Basilica of San Francesco, municipality, Comune di Arezzo]
  • A. Comune di Arezzo chosen
    Comune di Arezzo is the municipal government and administrative authority responsible for managing the city of Arezzo in Tuscany, Italy.
  • B. Comune di Siena
    Comune di Siena is the municipal government authority responsible for administering the city of Siena in Tuscany, Italy.
  • C. Comune di Montepulciano
    The Comune di Montepulciano is the municipal government authority responsible for administering the historic Tuscan hill town of Montepulciano in Italy.
  • D. Comune di Orvieto
    Comune di Orvieto is the municipal government and administrative authority responsible for managing the city and territory of Orvieto in the Umbria region of Italy.
  • E. Comune di Firenze
    Comune di Firenze is the municipal government of the city of Florence, responsible for its local administration, public services, and cultural heritage.
  • 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_69e0c45f17148190949c330ab9c27706 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69eeb5917fb88190a8d37831cced75dc completed April 27, 2026, 1:02 a.m.
Created at: April 16, 2026, 6:28 p.m.