Triple
T10513403
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GFMD |
E247971
|
entity |
| Predicate | supportedBy |
P67
|
FINISHED |
| Object | GFMD Support Unit |
E247973
|
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: GFMD Support Unit | Statement: [GFMD, supportedBy, GFMD Support Unit]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: GFMD Support Unit Context triple: [GFMD, supportedBy, GFMD Support Unit]
-
A.
GFMD Support Unit
chosen
The GFMD Support Unit is the administrative and coordination office that provides organizational, logistical, and technical support to the Global Forum on Migration and Development.
-
B.
GFMD
GFMD is an informal, state-led international platform that facilitates dialogue and cooperation on the interconnections between migration and development.
-
C.
GMD
GMD is a U.S. missile defense system designed to detect, track, and intercept long-range ballistic missiles during their midcourse phase in space.
-
D.
FGW
FGW is the National Rail station code for Fishguard and Goodwick railway station in Pembrokeshire, Wales.
-
E.
GFA
GFA is the ICAO airline designator used for Gulf Air, the national carrier of Bahrain.
- 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_69d381c4aa948190942e1d803143fb0e |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d509ca214481909b3ed9265e7a6704 |
completed | April 7, 2026, 1:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d90de6e9508190a1cdf348ec542dd5 |
completed | April 10, 2026, 2:49 p.m. |
Created at: April 6, 2026, 12:27 p.m.