Triple

T10714468
Position Surface form Disambiguated ID Type / Status
Subject St. Mary’s Tower E252624 entity
Predicate hasNameVariant P457 FINISHED
Object Santa Marija Tower E252623 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: Santa Marija Tower | Statement: [St. Mary’s Tower, hasNameVariant, Santa Marija Tower]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Santa Marija Tower
Context triple: [St. Mary’s Tower, hasNameVariant, Santa Marija Tower]
  • A. Santa Marija Tower chosen
    Santa Marija Tower is a 17th-century coastal watchtower on the Maltese island of Comino, historically used for coastal defense and maritime surveillance.
  • B. Gardoš Tower
    Gardoš Tower is a historic 19th-century lookout and memorial tower in the Zemun district of Belgrade, Serbia, known for its panoramic views over the Danube and the city.
  • C. Lotrščak Tower
    Lotrščak Tower is a historic medieval fortification and prominent landmark in Zagreb, Croatia, known for its daily cannon firing tradition.
  • D. Daliborka Tower
    Daliborka Tower is a late Gothic defensive tower and former prison located within Prague Castle in Prague, Czech Republic.
  • E. Donat Tower
    Donat Tower is a historic tower and notable architectural landmark located in the Saxon mining town of Freiberg, Germany.
  • 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_69d6aa5cbabc8190973e683950d89faf completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d6ff324d1881908b7cdf4ac208125f completed April 9, 2026, 1:21 a.m.
NED1 Entity disambiguation (via context triple) batch_69d9991f650881908d8db6e44b2c4543 completed April 11, 2026, 12:43 a.m.
Created at: April 8, 2026, 9:13 p.m.