Triple
T19102473
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fitiuta Airport |
E467568
|
entity |
| Predicate | IATA code |
P2569
|
FINISHED |
| Object | FTI |
—
|
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: FTI | Statement: [Fitiuta Airport, IATA code, FTI]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: FTI Context triple: [Fitiuta Airport, IATA code, FTI]
-
A.
FTI
chosen
FTI is the IATA airport code for Fitiuta Airport, a small public airport serving the village of Fitiuta on the island of Taʻū in American Samoa.
-
B.
TFI
TFI is the World Health Organization’s Tobacco Free Initiative, a program dedicated to reducing global tobacco use and its health impacts.
-
C.
TFI
TFI is the commonly used abbreviation for the Federal Supreme Court of Switzerland, the country’s highest judicial authority.
-
D.
TFI
TFI is the stock ticker symbol for the French media conglomerate TF1 Group, which operates television channels and related media services.
-
E.
FIHT
FIHT is an academic division focused on fostering innovation and advancing high technologies through education and research.
- 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_69d8dd05ac4c8190b1967d8f97f3fb2f |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e36e9bfc8190bbaccab169394d99 |
completed | April 20, 2026, 8:27 a.m. |
Created at: April 10, 2026, 12:04 p.m.