Triple
T15432893
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clean Government Party |
E369682
|
entity |
| Predicate | abbreviation |
P43
|
FINISHED |
| Object | CGP |
E369682
|
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: CGP | Statement: [Clean Government Party, abbreviation, CGP]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: CGP Context triple: [Clean Government Party, abbreviation, CGP]
-
A.
CGP
chosen
CGP is the abbreviation for Japan’s Clean Government Party, a political party known for its association with the Buddhist organization Soka Gakkai and its focus on pacifist and reformist policies.
-
B.
CGP
CGP is the IATA airport code for Shah Amanat International Airport serving Chittagong in Bangladesh.
-
C.
Collins Educational
Collins Educational is an imprint of the British publishing house William Collins, Sons, specializing in educational books and learning materials.
-
D.
Britannica School
Britannica School is an online educational resource platform from Encyclopaedia Britannica that provides age-appropriate, curriculum-aligned reference content and learning tools for students and educators.
-
E.
Cassell
Cassell is a British publishing company known for producing a wide range of books, including notable historical works and reference titles.
- 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_69d85a19180081909925012fbf4e62a3 |
completed | April 10, 2026, 2:02 a.m. |
| NER | Named-entity recognition | batch_69e03eda01cc8190843e23b260b8503c |
completed | April 16, 2026, 1:43 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff1a8546948190a69ae1306bc19c64 |
completed | May 9, 2026, 11:29 a.m. |
Created at: April 10, 2026, 3:21 a.m.