Triple

T9498823
Position Surface form Disambiguated ID Type / Status
Subject Weiden in der Oberpfalz E229081 entity
Predicate hasTwinTown P919 FINISHED
Object Marostica E770567 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: Marostica | Statement: [Weiden in der Oberpfalz, hasTwinTown, Marostica]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marostica
Context triple: [Weiden in der Oberpfalz, hasTwinTown, Marostica]
  • A. Marostica chosen
    Marostica is a historic town in northeastern Italy renowned for its medieval castle and life-sized human chess game played in the main square.
  • B. Legnago
    Legnago is a town in the Veneto region of northern Italy, situated along the Adige River and known historically as a fortified center.
  • C. Sacile
    Sacile is a historic town in northeastern Italy’s Friuli Venezia Giulia region, known for its picturesque river setting and strategic importance in various military conflicts.
  • D. Todi
    Todi is a historic hilltop town in central Italy known for its medieval architecture, scenic views over the Tiber Valley, and well-preserved city walls and churches.
  • E. Lodigiano
    Lodigiano is a regional variety of the Lombard language traditionally spoken in and around the city of Lodi in northern Italy.
  • 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_69ca84753660819098e8d416e89e26ae completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd983a94c48190a7ddf95a953c4ecc completed April 1, 2026, 10:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1af37e78081909683ce5359a8eb0e completed April 5, 2026, 12:39 a.m.
Created at: March 30, 2026, 7:56 p.m.