Triple
T10181508
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kirkuk |
E236794
|
entity |
| Predicate | hasAirport |
P105
|
FINISHED |
| Object |
Kirkuk Airport
Kirkuk Airport is a civilian and military airfield serving the city of Kirkuk in northern Iraq.
|
E845746
|
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: Kirkuk Airport | Statement: [Kirkuk, hasAirport, Kirkuk Airport]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kirkuk Airport Context triple: [Kirkuk, hasAirport, Kirkuk Airport]
-
A.
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.
-
B.
Mosul International Airport
Mosul International Airport is a major civilian and military airfield serving the city of Mosul in northern Iraq.
-
C.
Najaf International Airport
Najaf International Airport is a major Iraqi airport serving the holy city of Najaf, providing international air connections for religious pilgrims and other travelers.
-
D.
Jowhar Airport
Jowhar Airport is a public airfield serving the town of Jowhar in Somalia, providing regional air transport connections.
-
E.
Al-Hasakah Airport
Al-Hasakah Airport is a small regional airfield serving the city and surrounding region of Al-Hasakah in northeastern Syria.
- 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: Kirkuk Airport Triple: [Kirkuk, hasAirport, Kirkuk Airport]
Generated description
Kirkuk Airport is a civilian and military airfield serving the city of Kirkuk in northern Iraq.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Kirkuk Airport Target entity description: Kirkuk Airport is a civilian and military airfield serving the city of Kirkuk in northern Iraq.
-
A.
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.
-
B.
Mosul International Airport
Mosul International Airport is a major civilian and military airfield serving the city of Mosul in northern Iraq.
-
C.
Najaf International Airport
Najaf International Airport is a major Iraqi airport serving the holy city of Najaf, providing international air connections for religious pilgrims and other travelers.
-
D.
Jowhar Airport
Jowhar Airport is a public airfield serving the town of Jowhar in Somalia, providing regional air transport connections.
-
E.
Al-Hasakah Airport
Al-Hasakah Airport is a small regional airfield serving the city and surrounding region of Al-Hasakah in northeastern Syria.
- 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_69ca84d7260c8190bfbec36762943f37 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cded32b91c8190b01ad37b2456080a |
completed | April 2, 2026, 4:14 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d3013f0c54819092ee9c2c46fdf69e |
completed | April 6, 2026, 12:41 a.m. |
| NEDg | Description generation | batch_69d3028a4384819094a7daef7287e54f |
completed | April 6, 2026, 12:47 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d302e9d2688190bc292f8f2287c458 |
completed | April 6, 2026, 12:48 a.m. |
Created at: March 30, 2026, 9:12 p.m.