Triple
T23156754
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TFFF |
E578459
|
entity |
| Predicate | IATAcode |
P418
|
FINISHED |
| Object | FDF |
—
|
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: FDF | Statement: [TFFF, IATAcode, FDF]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: FDF Context triple: [TFFF, IATAcode, FDF]
-
A.
FDF
chosen
FDF is the IATA airport code for Martinique Aimé Césaire International Airport, the main air gateway to the Caribbean island of Martinique.
-
B.
EFD
EFD is the abbreviation for Switzerland’s Federal Department of Finance, the federal ministry responsible for national financial and budgetary policy.
-
C.
OFDF
The OFDF is the Swiss Federal Office for Customs and Border Security, responsible for overseeing customs procedures and safeguarding Switzerland’s borders.
-
D.
ADFdi
ADFdi is an Oracle ADF feature that lets users interact with enterprise applications directly from Microsoft Excel, enabling data entry, upload, and validation against ADF-based services.
-
E.
FDT
"FDT" is a politically charged protest song by YG featuring Nipsey Hussle that criticizes Donald Trump and became an anthem of opposition during the 2016 U.S. presidential election.
- 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_69e245fb8de081908f0eba7b5fd75bc4 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18efd598c81908fba9d583e30660e |
completed | April 29, 2026, 4:54 a.m. |
Created at: April 17, 2026, 4:01 p.m.