Triple
T16826487
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ibadan Airport |
E409031
|
entity |
| Predicate | IATA code |
P2569
|
FINISHED |
| Object |
IBA
IBA is the three-letter IATA airport code for Ibadan Airport serving the city of Ibadan in Nigeria.
|
E409031
|
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: IBA | Statement: [Ibadan Airport, IATA code, IBA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: IBA Context triple: [Ibadan Airport, IATA code, IBA]
-
A.
IBA
IBA is the commonly used abbreviation for the International Bartenders Association, a global organization that standardizes cocktail recipes and supports professional bartenders worldwide.
-
B.
IBA
IBA is the standard abbreviation for Important Bird Area, a globally recognized designation for sites critical to the conservation of bird populations and biodiversity.
-
C.
IBA
IBA is the International Bar Association, a leading global organization of legal professionals and bar associations that works to shape the future of the legal profession and uphold the rule of law worldwide.
-
D.
IBA
IBA is the international governing body responsible for overseeing and regulating amateur boxing competitions worldwide.
-
E.
IBA
IBA is the principal industry body representing banking and financial institutions in India, coordinating policy, advocacy, and common initiatives for its member banks.
- 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: IBA Triple: [Ibadan Airport, IATA code, IBA]
Generated description
IBA is the three-letter IATA airport code for Ibadan Airport serving the city of Ibadan in Nigeria.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: IBA Target entity description: IBA is the three-letter IATA airport code for Ibadan Airport serving the city of Ibadan in Nigeria.
-
A.
IBA
chosen
IBA is the IATA airport code for Ibadan Airport, a domestic airport serving the city of Ibadan in southwestern Nigeria.
-
B.
IBA
IBA is the standard abbreviation for Important Bird Area, a globally recognized designation for sites critical to the conservation of bird populations and biodiversity.
-
C.
IBA
IBA is the commonly used abbreviation for the International Bartenders Association, a global organization that standardizes cocktail recipes and supports professional bartenders worldwide.
-
D.
IBA
IBA is the International Bar Association, a leading global organization of legal professionals and bar associations that works to shape the future of the legal profession and uphold the rule of law worldwide.
-
E.
IBA
IBA is the principal industry body representing banking and financial institutions in India, coordinating policy, advocacy, and common initiatives for its member banks.
- F. None of above.
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_69d88394566c8190b3dcbdc72935f7fa |
completed | April 10, 2026, 4:59 a.m. |
| NER | Named-entity recognition | batch_69e3b31404c88190a3b2802842ca77eb |
completed | April 18, 2026, 4:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00b29e48f881908489bd77a9caec97 |
completed | May 10, 2026, 4:30 p.m. |
| NEDg | Description generation | batch_6a00b3aafac08190b3e0181780f45392 |
completed | May 10, 2026, 4:34 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a00b466ecd08190b7b5ee54476631ab |
completed | May 10, 2026, 4:37 p.m. |
Created at: April 10, 2026, 5:23 a.m.