Triple
T14361483
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lomé–Tokoin International Airport |
E356113
|
entity |
| Predicate | IATAcode |
P418
|
FINISHED |
| Object | LFW |
E356114
|
NE FINISHED |
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: LFW | Statement: [Lomé–Tokoin International Airport, IATAcode, LFW]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: LFW Context triple: [Lomé–Tokoin International Airport, IATAcode, LFW]
-
A.
LFW
chosen
LFW is the IATA airport code for Lomé–Tokoin International Airport, the main airport serving Lomé, the capital of Togo.
-
B.
CelebA
CelebA is a large-scale face attributes dataset widely used in computer vision research for tasks like facial recognition, attribute prediction, and generative modeling.
-
C.
Faces Places
Faces Places is a 2017 French documentary film co-directed by Agnès Varda and artist JR, in which they travel through rural France creating large-scale photographic portraits while reflecting on memory, community, and aging.
-
D.
FFHQ
FFHQ (Flickr-Faces-HQ) is a high-quality, large-scale dataset of diverse human face images widely used for training and evaluating generative image models.
-
E.
ORL
ORL is the standard three-letter abbreviation used for the NBA team Orlando Magic.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d82790a7e08190877e2d349b2e8d8e |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de8fabec088190bd8128371b29e958 |
completed | April 14, 2026, 7:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd4c4aba788190bd5ab8cbc772dcf1 |
completed | May 8, 2026, 2:36 a.m. |
Created at: April 10, 2026, 1:15 a.m.