Triple
T23107367
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terminal T9 |
E576210
|
entity |
| Predicate | associatedWithIATAAirportCode |
P45234
|
FINISHED |
| Object | CDG |
—
|
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: CDG | Statement: [Terminal T9, associatedWithIATAAirportCode, CDG]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: CDG Context triple: [Terminal T9, associatedWithIATAAirportCode, CDG]
-
A.
CDG
chosen
CDG is the IATA airport code for Charles de Gaulle Airport, the main international airport serving Paris and one of Europe’s busiest air hubs.
-
B.
CDGVAL
CDGVAL is the automated light-rail shuttle system that links the terminals and key facilities within Paris Charles de Gaulle Airport.
-
C.
CGD
CGD is the IATA airport code for Changde Taohuayuan Airport in Changde, Hunan Province, China.
-
D.
CGR
CGR is the IATA airport code for Campo Grande International Airport in Campo Grande, Brazil.
-
E.
CGR
CGR is the acronym for Chile’s Comptroller General, the autonomous public body responsible for overseeing the legality and proper use of public funds and administrative acts in the country.
- 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_69e245f4af548190898d434a64a1e774 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18e0c7b9c8190b1160485eae87c9b |
completed | April 29, 2026, 4:50 a.m. |
Created at: April 17, 2026, 3:58 p.m.