Triple

T10337317
Position Surface form Disambiguated ID Type / Status
Subject Mamluk Arabic E243040 entity
Predicate usedIn P98 FINISHED
Object Damascus E14526 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: Damascus | Statement: [Mamluk Arabic, usedIn, Damascus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Damascus
Context triple: [Mamluk Arabic, usedIn, Damascus]
  • A. Damascus chosen
    Damascus is the capital and one of the largest cities of Syria, renowned as one of the oldest continuously inhabited cities in the world and a historic cultural and commercial center of the Arab world.
  • B. Aleppo
    Aleppo is an ancient and historically significant city in northern Syria, renowned for its rich cultural heritage, medieval architecture, and role as a major trading hub along the Silk Road.
  • C. Maidin
    Maidin is a Malay family name notably borne by Rashid Maidin, a prominent figure in Malaysian political history.
  • D. Ashdad
    Ashdad is a small community located within the township of Greater Madawaska in eastern Ontario, Canada.
  • E. Tartus
    Tartus is a major Syrian port city on the Mediterranean coast that hosts Russia’s only naval facility outside the former Soviet Union.
  • 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_69d381af787481908bc401325c760a88 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4e0a3a8e4819097268ce101dec2d1 completed April 7, 2026, 10:46 a.m.
NED1 Entity disambiguation (via context triple) batch_69d794fe4fe481908e4c343ceeb5de25 completed April 9, 2026, 12:01 p.m.
Created at: April 6, 2026, 11:54 a.m.