Triple
T22728673
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | VIGR |
E562066
|
entity |
| Predicate | hasIATACode |
P2569
|
FINISHED |
| Object | GWL |
—
|
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: GWL | Statement: [VIGR, hasIATACode, GWL]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: GWL Context triple: [VIGR, hasIATACode, GWL]
-
A.
GWL
GWL is the station code for Gwalior Junction, a major railway hub in the Indian state of Madhya Pradesh.
-
B.
GWL
chosen
GWL is the IATA airport code for Gwalior Airport, serving the city of Gwalior in the Indian state of Madhya Pradesh.
-
C.
GLW
GLW is the stock ticker symbol for Corning Incorporated, a leading American manufacturer specializing in glass, ceramics, and related advanced materials used in industries such as telecommunications, consumer electronics, and life sciences.
-
D.
GWI
GWI is the National Rail station code for Greenwich railway station in London, England.
-
E.
GW
GW (Gesamtkatalog der Wiegendrucke) is a comprehensive scholarly catalog of incunabula, documenting books printed in Europe before 1501.
- 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_69e24550859c81908727d91efc3a81b4 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f1792b22cc819099aa00bb2dbacce3 |
completed | April 29, 2026, 3:21 a.m. |
Created at: April 17, 2026, 3:21 p.m.