Triple
T11564533
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Seoul–New York |
E274221
|
entity |
| Predicate | IATACodeOrigin |
P418
|
FINISHED |
| Object | ICN |
E470414
|
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: ICN | Statement: [Seoul–New York, IATACodeOrigin, ICN]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ICN Context triple: [Seoul–New York, IATACodeOrigin, ICN]
-
A.
ICN
ICN is a global network of competition authorities that promotes cooperation and convergence in antitrust enforcement and policy.
-
B.
ICN
ICN is the internationally accepted set of rules and recommendations that governs the scientific naming of algae, fungi, and plants.
-
C.
ICN
chosen
ICN is the IATA airport code for Incheon International Airport, South Korea’s largest and primary international gateway serving the Seoul metropolitan area.
-
D.
ICCN
ICCN is the national authority responsible for managing and protecting protected areas and wildlife in the Democratic Republic of the Congo.
-
E.
ICCR
ICCR is an autonomous Indian government organization dedicated to promoting the country’s cultural diplomacy and fostering cultural exchange with nations around the world.
- 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_69d6aae5ac3c81908d2b0a3a665665b2 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d88dd321f88190a57ecaf079fbbc3f |
completed | April 10, 2026, 5:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e6e8b1a67481909a05105728acc358 |
completed | April 21, 2026, 3:02 a.m. |
Created at: April 8, 2026, 9:37 p.m.