Triple
T10247213
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Léon-Mba International Airport |
E240246
|
entity |
| Predicate | IATAcode |
P418
|
FINISHED |
| Object |
LBV
LBV is the IATA airport code for Léon-Mba International Airport, the main international gateway serving Libreville, the capital of Gabon.
|
E853674
|
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: LBV | Statement: [Léon-Mba International Airport, IATAcode, LBV]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: LBV Context triple: [Léon-Mba International Airport, IATAcode, LBV]
-
A.
BVL
BVL is Germany’s Federal Office of Consumer Protection and Food Safety, the national authority responsible for ensuring food safety and protecting consumer health.
-
B.
LBG
LBG is the IATA airport code for Paris–Le Bourget Airport, a historic airfield near Paris known for hosting the Paris Air Show.
-
C.
LBN
LBN is the three-letter ISO 3166-1 alpha-3 country code for Lebanon.
-
D.
BV
BV is the two-letter ISO 3166 country code assigned to Bouvet Island, a remote uninhabited Norwegian territory in the South Atlantic Ocean.
-
E.
LB
LB is the former New York Stock Exchange ticker symbol for L Brands, the American retail company that owned brands such as Victoria’s Secret and Bath & Body Works.
- 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: LBV Triple: [Léon-Mba International Airport, IATAcode, LBV]
Generated description
LBV is the IATA airport code for Léon-Mba International Airport, the main international gateway serving Libreville, the capital of Gabon.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: LBV Target entity description: LBV is the IATA airport code for Léon-Mba International Airport, the main international gateway serving Libreville, the capital of Gabon.
-
A.
BVL
BVL is Germany’s Federal Office of Consumer Protection and Food Safety, the national authority responsible for ensuring food safety and protecting consumer health.
-
B.
LBG
LBG is the IATA airport code for Paris–Le Bourget Airport, a historic airfield near Paris known for hosting the Paris Air Show.
-
C.
LBN
LBN is the three-letter ISO 3166-1 alpha-3 country code for Lebanon.
-
D.
BV
BV is the two-letter ISO 3166 country code assigned to Bouvet Island, a remote uninhabited Norwegian territory in the South Atlantic Ocean.
-
E.
LB
LB is the former New York Stock Exchange ticker symbol for L Brands, the American retail company that owned brands such as Victoria’s Secret and Bath & Body Works.
- 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_69d381a7e198819090280d5ab885d59e |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d22e0d4c8190a6712859924e9d3d |
completed | April 7, 2026, 9:45 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d6f7ade8448190830d950b7cee0c34 |
completed | April 9, 2026, 12:49 a.m. |
| NEDg | Description generation | batch_69d6fa303d4c8190b9f1c3addf7d8b09 |
completed | April 9, 2026, 1 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d6ff301d488190b18f1e02bbf1dada |
completed | April 9, 2026, 1:21 a.m. |
Created at: April 6, 2026, 11:27 a.m.