Triple
T20920077
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Iki Airport |
E515182
|
entity |
| Predicate | IATACode |
P418
|
FINISHED |
| Object | IKI |
—
|
NE NERFINISHED |
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: IKI | Statement: [Iki Airport, IATACode, IKI]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: IKI Context triple: [Iki Airport, IATACode, IKI]
-
A.
IKI
chosen
IKI is the IATA airport code for Iki Airport, a regional airport serving Iki Island in Nagasaki Prefecture, Japan.
-
B.
IKI RAS
IKI RAS is a leading Russian space science institute under the Russian Academy of Sciences, specializing in space physics, planetary research, and astrophysics missions.
-
C.
Iki
Iki is one of the signature illumination themes of Tokyo Skytree, featuring an elegant, cool-toned lighting design inspired by traditional Edo aesthetics.
-
D.
Iki
Iki is a Japanese island city in Nagasaki Prefecture known for its coastal scenery, historical sites, and connection to nearby Kyushu and Korea.
-
E.
Ikire
Ikire is a prominent town in southwestern Nigeria known for its location along major transport routes and its distinctive local delicacies, particularly “dodo Ikire.”
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4f9d5ec8190bb2bd27350ed341c |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6ec677338819081410cbaa2846260 |
completed | April 21, 2026, 3:17 a.m. |
Created at: April 16, 2026, 12:48 p.m.