Triple

T23400962
Position Surface form Disambiguated ID Type / Status
Subject IS E559502 entity
Predicate claimedCapital P204 FINISHED
Object Raqqa 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: Raqqa | Statement: [IS, claimedCapital, Raqqa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Raqqa
Context triple: [IS, claimedCapital, Raqqa]
  • A. Raqqa chosen
    Raqqa is a city in northern Syria that became widely known as the de facto capital of the Islamic State (ISIS) during its control from 2014 to 2017.
  • B. Raqqa Governorate
    Raqqa Governorate is an administrative region in northern Syria centered on the city of Raqqa, known for its location along the Euphrates River and its recent prominence in the Syrian conflict.
  • C. Khan Shaykhun
    Khan Shaykhun is a town in northwestern Syria that gained international attention during the Syrian civil war, particularly after a widely reported chemical attack in 2017.
  • D. Tal Afar
    Tal Afar is a predominantly Iraqi Turkmen city in northwestern Iraq known for its strategic location near Mosul and the Syrian border and for being a focal point in various phases of the Iraq conflict.
  • E. Homs
    Homs is one of Syria’s largest and oldest cities, historically a major commercial and industrial center located in the western part of the country.
  • 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_69e24549610c8190a069d6411ce5f661 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1a4dfa4c881908df0eced4855c0d9 completed April 29, 2026, 6:27 a.m.
Created at: April 17, 2026, 5:37 p.m.