Triple
T842287
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yemen |
E18202
|
entity |
| Predicate | memberOf |
P10
|
FINISHED |
| Object | G77 |
E5828
|
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: G77 | Statement: [Yemen, memberOf, G77]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: G77 Context triple: [Yemen, memberOf, G77]
-
A.
G77
chosen
The G77 is a coalition of developing nations within the United Nations that coordinates members’ economic interests and promotes collective negotiating power on global issues.
-
B.
UN M49
UN M49 is a United Nations standard that defines numeric codes for countries and geographical regions for statistical and analytical purposes.
-
C.
ACP Group of States
The ACP Group of States is an intergovernmental organization of African, Caribbean, and Pacific countries primarily focused on sustainable development and cooperation with the European Union.
-
D.
Group of Eight
The Group of Eight is a coalition of leading Australian research-intensive universities known for their strong focus on high-quality education and influential research output.
-
E.
G7
G7 is an intergovernmental forum of seven major advanced economies that coordinates on global economic policy, security, and international issues.
- 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_69a4938b04208190b82e1df6b572c548 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4abe8a0bc81909b54af465e67be1f |
completed | March 1, 2026, 9:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a7929a91088190bef474424bde527c |
completed | March 4, 2026, 2:02 a.m. |
Created at: March 1, 2026, 7:38 p.m.