Triple

T17020598
Position Surface form Disambiguated ID Type / Status
Subject Liri Valley E412936 entity
Predicate near P350 FINISHED
Object Monte Cassino E361878 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: Monte Cassino | Statement: [Liri Valley, near, Monte Cassino]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Monte Cassino
Context triple: [Liri Valley, near, Monte Cassino]
  • A. Monte Cassino chosen
    Monte Cassino is a historic hilltop abbey in Italy, renowned as one of the oldest monasteries in Western Christianity and as the site of a major World War II battle.
  • B. Monte Martica
    Monte Martica is a mountain in the Lombardy region of northern Italy, known for its forested slopes and hiking trails overlooking the surrounding Varese area.
  • C. Rocca Pia
    Rocca Pia is a 15th-century fortress in Tivoli, Italy, built under Pope Pius II to strengthen papal control and now a notable historical landmark.
  • D. Monte San Savino
    Monte San Savino is a historic Tuscan town in central Italy known for its medieval architecture and Renaissance heritage.
  • E. Rocca del Leone
    Rocca del Leone is a medieval lakeside fortress in Castiglione del Lago, Italy, known for its well-preserved walls and panoramic views over Lake Trasimeno.
  • 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_69d886cc4170819093deddc7b8b4b6a7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d482c3a0819099e6ea4acb0a08ee completed April 18, 2026, 6:59 p.m.
NED1 Entity disambiguation (via context triple) batch_6a011b4f9dfc819085639edb5cda1cca completed May 10, 2026, 11:57 p.m.
Created at: April 10, 2026, 5:33 a.m.