Triple

T13847786
Position Surface form Disambiguated ID Type / Status
Subject Tal Afar E332852 entity
Predicate hasAirport P105 FINISHED
Object Tal Afar Airport
Tal Afar Airport is a military airfield in northern Iraq that has been strategically significant in regional conflicts and security operations.
E1065717 NE FINISHED

How this triple was built (4 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: Tal Afar Airport | Statement: [Tal Afar, hasAirport, Tal Afar Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tal Afar Airport
Context triple: [Tal Afar, hasAirport, Tal Afar Airport]
  • A. Deir ez-Zor Airport
    Deir ez-Zor Airport is a small civilian and military airfield serving the city of Deir ez-Zor in eastern Syria.
  • B. Kirkuk Airport
    Kirkuk Airport is a civilian and military airfield serving the city of Kirkuk in northern Iraq.
  • C. Erbil International Airport
    Erbil International Airport is a major civilian and military airport serving the city of Erbil and the wider Kurdistan Region in northern Iraq.
  • D. Al-Hasakah Airport
    Al-Hasakah Airport is a small regional airfield serving the city and surrounding region of Al-Hasakah in northeastern Syria.
  • E. Jowhar Airport
    Jowhar Airport is a public airfield serving the town of Jowhar in Somalia, providing regional air transport connections.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Tal Afar Airport
Triple: [Tal Afar, hasAirport, Tal Afar Airport]
Generated description
Tal Afar Airport is a military airfield in northern Iraq that has been strategically significant in regional conflicts and security operations.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tal Afar Airport
Target entity description: Tal Afar Airport is a military airfield in northern Iraq that has been strategically significant in regional conflicts and security operations.
  • A. Deir ez-Zor Airport
    Deir ez-Zor Airport is a small civilian and military airfield serving the city of Deir ez-Zor in eastern Syria.
  • B. Kirkuk Airport
    Kirkuk Airport is a civilian and military airfield serving the city of Kirkuk in northern Iraq.
  • C. Erbil International Airport
    Erbil International Airport is a major civilian and military airport serving the city of Erbil and the wider Kurdistan Region in northern Iraq.
  • D. Al-Hasakah Airport
    Al-Hasakah Airport is a small regional airfield serving the city and surrounding region of Al-Hasakah in northeastern Syria.
  • E. Jowhar Airport
    Jowhar Airport is a public airfield serving the town of Jowhar in Somalia, providing regional air transport connections.
  • F. None of above. chosen

Provenance (5 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_69d81c5ba13c8190839315f54768acfd completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de02b2a9788190b164760adec64ef6 completed April 14, 2026, 9:02 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7c0f189008190bb9afeef42564a33 completed May 3, 2026, 9:41 p.m.
NEDg Description generation batch_69f7c23410dc8190972245cecfa85871 completed May 3, 2026, 9:46 p.m.
NED2 Entity disambiguation (via description) batch_69f7c3031a0c8190ad30d59fe1f2322e completed May 3, 2026, 9:49 p.m.
Created at: April 9, 2026, 10:14 p.m.