Triple
T21422419
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MPI |
E528468
|
entity |
| Predicate | governingBody |
P46
|
FINISHED |
| Object | MPI Forum |
—
|
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: MPI Forum | Statement: [MPI, governingBody, MPI Forum]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MPI Forum Context triple: [MPI, governingBody, MPI Forum]
-
A.
MPI
MPI is a global measure that assesses poverty by considering multiple deprivations in areas such as health, education, and living standards rather than income alone.
-
B.
MPI
chosen
MPI (Message Passing Interface) is a standardized and portable communication protocol widely used for parallel programming in high-performance computing environments.
-
C.
MPI Discovery
MPI Discovery is a purpose-built offshore wind turbine installation vessel used for constructing large-scale wind farms at sea.
-
D.
MPI Adventure
MPI Adventure is a purpose-built offshore wind turbine installation vessel known for its role in constructing large-scale wind farms such as the London Array in the North Sea.
-
E.
MPIP
MPIP is a leading German research institute focused on cutting-edge fundamental and applied research in polymer science and soft materials.
- 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_69e0c455f3688190810bc96365791b0f |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e8b2d17f5081908f0185011eae3160 |
completed | April 22, 2026, 11:36 a.m. |
Created at: April 16, 2026, 5:48 p.m.