Triple
T20804685
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FMAP |
E512124
|
entity |
| Predicate | hasAbbreviation |
P43
|
FINISHED |
| Object | FMAP |
—
|
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: FMAP | Statement: [FMAP, hasAbbreviation, FMAP]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: FMAP Context triple: [FMAP, hasAbbreviation, FMAP]
-
A.
FMAP
chosen
FMAP is the federal government’s share of Medicaid program costs, used to determine how much federal funding each state receives for eligible medical services.
-
B.
FAPM
FAPM is the ICAO airport code for Pietermaritzburg Airport in Pietermaritzburg, South Africa.
-
C.
FPM
FPM is the Fellow Programme in Management, a doctoral-level research program in management studies offered by the Indian Institutes of Management.
-
D.
FMU
FMU is a public university in Florence, South Carolina, known for its liberal arts and professional programs.
-
E.
EMAP
EMAP is a media and events company known for organizing and supporting major international architecture and design initiatives.
- 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_69e0b4cc69f481908e98751e697b9df4 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c2ce6420819091792ffaa3c46c53 |
completed | April 21, 2026, 12:20 a.m. |
Created at: April 16, 2026, 12:40 p.m.