Triple
T12399978
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Juanda International Airport |
E296225
|
entity |
| Predicate | iataCode |
P2569
|
FINISHED |
| Object | SUB |
E296224
|
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: SUB | Statement: [Juanda International Airport, iataCode, SUB]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SUB Context triple: [Juanda International Airport, iataCode, SUB]
-
A.
SUB
chosen
SUB is the IATA airport code for Juanda International Airport serving Surabaya, Indonesia.
-
B.
subant
subant is an Apache Ant task that allows one build script to invoke and control other Ant build files as part of a larger build process.
-
C.
Subcon
Subcon is the dreamlike fantasy world that serves as the primary backdrop for the video game Super Mario Bros. 2.
-
D.
SB
SB is the abbreviated name for the School of Basic Sciences, an academic unit focused on foundational scientific disciplines.
-
E.
SB
SB was the communist-era secret police and intelligence service of the Polish People's Republic, known for surveillance, repression, and political control.
- 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_69d6ad9f464c81909db36d7e96e34b9e |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d9401cbfd481908ee6e765da3d12cb |
completed | April 10, 2026, 6:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f63482af8c8190b277b36371979f5e |
completed | May 2, 2026, 5:29 p.m. |
Created at: April 8, 2026, 9:55 p.m.