Triple
T13588436
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kereta Api Indonesia |
E324630
|
entity |
| Predicate | hasAbbreviation |
P43
|
FINISHED |
| Object | KAI |
E628696
|
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: KAI | Statement: [Kereta Api Indonesia, hasAbbreviation, KAI]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: KAI Context triple: [Kereta Api Indonesia, hasAbbreviation, KAI]
-
A.
KAL
KAL is the standard abbreviation used for the Kalamazoo Growlers baseball team.
-
B.
KAL
KAL is the ICAO airline designator used to identify Korean Air in international aviation operations.
-
C.
KAI Commuter
chosen
KAI Commuter is an Indonesian railway company that operates commuter rail services in the Greater Jakarta area and surrounding regions.
-
D.
KIAD
KIAD is the ICAO airport code for Washington Dulles International Airport, a major international air travel hub serving the Washington, D.C. metropolitan area.
-
E.
KJ-500
The KJ-500 is a modern Chinese airborne early warning and control (AEW&C) aircraft featuring a fixed dorsal radar dome and advanced phased-array radar systems for long-range airspace surveillance and battle management.
- 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_69d80769100c819099111274614f5ed2 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbb054c6008190839384ce26e8f71a |
completed | April 12, 2026, 2:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f76bc347b881908267455f3bdd50e8 |
completed | May 3, 2026, 3:37 p.m. |
Created at: April 9, 2026, 9:49 p.m.