Triple
T347113
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gare de Lyon |
E6964
|
entity |
| Predicate | hasIATACode |
P2569
|
FINISHED |
| Object | XPG |
E37923
|
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: XPG | Statement: [Gare de Lyon, hasIATACode, XPG]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: XPG Context triple: [Gare de Lyon, hasIATACode, XPG]
-
A.
XPG
chosen
XPG is the IATA station code for Paris Gare du Nord, one of the main international railway hubs in Paris, France.
-
B.
KIX
KIX is the three-letter IATA airport code for Kansai International Airport serving the Osaka region of Japan.
-
C.
Buffalo Bell
Buffalo Bell is a female buffalo mascot character for the Japanese professional baseball team Orix Buffaloes.
-
D.
Cree
The Cree are one of the largest Indigenous peoples of North America, with communities primarily in Canada and a rich cultural heritage including distinct Algonquian languages and traditions.
-
E.
Onex
Onex is a suburban municipality in western Switzerland located just outside the city of Geneva.
- 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_69a2e7951ba08190960e90823b5078f3 |
completed | Feb. 28, 2026, 1:03 p.m. |
| NER | Named-entity recognition | batch_69a2eb1a37c08190b1380f6bf8513a37 |
completed | Feb. 28, 2026, 1:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a3d7eb6b708190b0dff991c101104f |
completed | March 1, 2026, 6:08 a.m. |
Created at: Feb. 28, 2026, 1:08 p.m.