Triple

T20323348
Position Surface form Disambiguated ID Type / Status
Subject Siege of Melilla E492264 entity
Predicate location P40 FINISHED
Object Melilla 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: Melilla | Statement: [Siege of Melilla, location, Melilla]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Melilla
Context triple: [Siege of Melilla, location, Melilla]
  • A. Melilla chosen
    Melilla is a Spanish autonomous city located on the north coast of Africa, bordering Morocco and serving as a key enclave between Europe and Africa.
  • B. Algeciras
    Algeciras is a major port city in southern Spain, strategically located near the Strait of Gibraltar and serving as a key hub for maritime trade between Europe and Africa.
  • C. Algeciras
    Algeciras is a municipality in the Huila Department of southwestern Colombia, known for its agricultural economy and Andean rural landscapes.
  • D. Ceuta
    Ceuta is a small Spanish autonomous city on the north coast of Africa, bordering Morocco and strategically located at the Strait of Gibraltar.
  • E. Malaga
    Malaga is a white wine grape variety name historically used as a synonym for Sémillon in certain wine-growing regions.
  • 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_69e0b4a0134081909113563e1c3ba68a completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6778d95dc81909b1c87d26b5d3a33 completed April 20, 2026, 6:59 p.m.
Created at: April 16, 2026, 11:21 a.m.