Triple
T17547540
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | San Cristóbal Airport |
E427367
|
entity |
| Predicate | IATAcode |
P418
|
FINISHED |
| Object | SCY |
—
|
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: SCY | Statement: [San Cristóbal Airport, IATAcode, SCY]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SCY Context triple: [San Cristóbal Airport, IATAcode, SCY]
-
A.
SCY
chosen
SCY is the IATA airport code for San Cristóbal Airport, which serves San Cristóbal Island in Ecuador’s Galápagos archipelago.
-
B.
SYC
SYC is the abbreviation for the Syariah Court of Singapore, a judicial body that administers Muslim family law matters in Singapore.
-
C.
SWIM
SWIM is a subsystem within the SARA framework, likely responsible for a specific functional module such as data handling, communication, or workflow management.
-
D.
S&C
S&C is the commonly used abbreviation for Southbound & Crown, a name typically associated with a brand, venue, or business entity.
-
E.
SC6
SC6 is a rebranded, personality-driven edition of ESPN’s SportsCenter that was hosted by Michael Smith and Jemele Hill in the 6 p.m. time slot.
- 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_69d889df6dc081908f67dbadc03c07ee |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e454626cfc8190a2602ba4934b8e6d |
completed | April 19, 2026, 4:04 a.m. |
Created at: April 10, 2026, 5:49 a.m.