Triple
T14112768
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SCGZ |
E339680
|
entity |
| Predicate | hasIATACode |
P2569
|
FINISHED |
| Object | WPU |
E339679
|
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: WPU | Statement: [SCGZ, hasIATACode, WPU]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: WPU Context triple: [SCGZ, hasIATACode, WPU]
-
A.
WPU
WPU is the IATA airport code for Robinson Crusoe Island Airfield, a small airport serving Robinson Crusoe Island in Chile.
-
B.
WPU
chosen
WPU is the IATA airport code for Guardiamarina Zañartu Airport, a small regional airport serving Puerto Williams in southern Chile.
-
C.
WPU
WPU is a private liberal arts university located in Raleigh, North Carolina, known for its small class sizes and career-focused undergraduate programs.
-
D.
WU
WU is the stock ticker symbol for Western Union, a global financial services company best known for its money transfer and payment services.
-
E.
WU
WU is a leading European university in Vienna specializing in economics, business, and social sciences.
- 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_69d81c6a95b481909e39111e0c1f31ee |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de600f992c81908133813f2894dcca |
completed | April 14, 2026, 3:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcdf04871c8190891605415f1abf7f |
completed | May 7, 2026, 6:50 p.m. |
Created at: April 9, 2026, 10:22 p.m.