Triple
T11524905
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Seoul–Frankfurt |
E273266
|
entity |
| Predicate | IATADestinationCode |
P418
|
FINISHED |
| Object | FRA |
E440597
|
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: FRA | Statement: [Seoul–Frankfurt, IATADestinationCode, FRA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: FRA Context triple: [Seoul–Frankfurt, IATADestinationCode, FRA]
-
A.
FRA
FRA is the three-letter ISO 3166-1 alpha-3 country code that uniquely identifies France in international standards and data systems.
-
B.
FRA
FRA is the United States government agency responsible for regulating and overseeing the nation’s railroad safety, infrastructure, and operations.
-
C.
FRA
FRA is the standard abbreviation used to refer to the Royal Moroccan Air Force, the aerial warfare branch of Morocco’s armed forces.
-
D.
FRA
FRA is the acronym for the Global Forest Resources Assessment, a periodic FAO-led study that evaluates the state and trends of the world’s forests.
-
E.
FRA
chosen
FRA is the three-letter IATA airport code for Frankfurt Airport, one of Europe’s busiest international aviation hubs located in Frankfurt, Germany.
- 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_69d6aae3fbec8190a14632a5df2538b6 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d87fd26648819083de19bcddf8ad69 |
completed | April 10, 2026, 4:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e62562efb88190bbf3c7bbec8233aa |
completed | April 20, 2026, 1:08 p.m. |
Created at: April 8, 2026, 9:37 p.m.