Triple
T21849542
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kualanamu International Airport |
E539466
|
entity |
| Predicate | ICAOcode |
P419
|
FINISHED |
| Object | WIMM |
—
|
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: WIMM | Statement: [Kualanamu International Airport, ICAOcode, WIMM]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: WIMM Context triple: [Kualanamu International Airport, ICAOcode, WIMM]
-
A.
WIMM
chosen
WIMM is the ICAO airport code for Kualanamu International Airport, a major airport serving Medan and the surrounding region in North Sumatra, Indonesia.
-
B.
WIM
WIM is the National Rail station code for Wimbledon railway station in southwest London.
-
C.
WIMK
WIMK is the former ICAO airport code once assigned to Polonia International Airport in Indonesia.
-
D.
WIM PW
WIM PW is the commonly used abbreviation for the Faculty of Materials Science and Engineering at the Warsaw University of Technology, a leading Polish center for education and research in materials engineering.
-
E.
WAMM
WAMM is the ICAO airport code for Sam Ratulangi International Airport serving Manado in North Sulawesi, Indonesia.
- 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_69e0c476c3c88190a92d08ebb59a128a |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f0bd582ca48190890648fdee2a0c6e |
completed | April 28, 2026, 1:59 p.m. |
Created at: April 16, 2026, 6:55 p.m.