Triple
T6265806
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Global Drug Facility |
E140410
|
entity |
| Predicate | abbreviation |
P43
|
FINISHED |
| Object | GDF |
E140410
|
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: GDF | Statement: [Global Drug Facility, abbreviation, GDF]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: GDF Context triple: [Global Drug Facility, abbreviation, GDF]
-
A.
GDF
chosen
GDF is the Global Drug Facility, an international mechanism that supplies quality-assured medicines and diagnostics to support tuberculosis control and treatment programs worldwide.
-
B.
GdF
GdF is the commonly used abbreviation for Italy’s Guardia di Finanza, a militarized police force responsible for financial crime, smuggling, and border control.
-
C.
GF
GF is the vehicle registration code assigned to the district that includes the Austrian town of Deutsch-Wagram.
-
D.
GF
GF is the two-letter ISO 3166-1 alpha-2 country code assigned to French Guiana.
-
E.
GDN
GDN is the vehicle registration code assigned to motor vehicles registered in the Pomeranian Voivodeship of Poland.
- 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_69c008cabc4081909723e2547c9d6cc0 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c0639e64588190875e4e1e772fb336 |
completed | March 22, 2026, 9:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c51932e704819083e1ed17a86f6b5e |
completed | March 26, 2026, 11:32 a.m. |
Created at: March 22, 2026, 4:25 p.m.