Triple

T21589161
Position Surface form Disambiguated ID Type / Status
Subject Moorish Castle E532733 entity
Predicate creator P184 FINISHED
Object Moors 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: Moors | Statement: [Moorish Castle, creator, Moors]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Moors
Context triple: [Moorish Castle, creator, Moors]
  • A. Moors
    Moors is a surname of English origin that appears as the middle name of American businessman and philanthropist John Moors Cabot.
  • B. Moors chosen
    The Moors were medieval Muslim inhabitants of the Maghreb, Iberian Peninsula, and parts of Western Africa, known for their significant cultural, scientific, and architectural influence on Europe, especially in Spain and Portugal.
  • C. Muslim Moors
    Muslim Moors are a Muslim ethnic community of Arab and local descent primarily found in Sri Lanka, historically known for their role in trade and cultural exchange.
  • D. Mouriscas
    Mouriscas is a civil parish in the municipality of Abrantes, located in central Portugal.
  • E. Awraba Berbers
    The Awraba Berbers were an influential Berber tribe of North Africa, prominent in early Islamic-era Morocco and known for their political and military role in the region.
  • 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_69e0c46251648190876f0427cf2d321b completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69eefadb25108190b7a3d2e8dfc8ae60 completed April 27, 2026, 5:57 a.m.
Created at: April 16, 2026, 6:32 p.m.