Triple
T23483837
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CEPT Scheme Agreement |
E570475
|
entity |
| Predicate | abbreviation |
P43
|
FINISHED |
| Object | CEPT |
—
|
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: CEPT | Statement: [CEPT Scheme Agreement, abbreviation, CEPT]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: CEPT Context triple: [CEPT Scheme Agreement, abbreviation, CEPT]
-
A.
CEPT
CEPT is an Indian university in Ahmedabad renowned for its programs in architecture, planning, design, and related built-environment disciplines.
-
B.
CEPT
chosen
CEPT is a European intergovernmental organization that coordinates postal and telecommunications policies and regulations among its member countries.
-
C.
CONT
CONT is the European Parliament’s Committee on Budgetary Control, responsible for overseeing the implementation and proper use of the European Union budget.
-
D.
CON
CON is the stock ticker symbol for Continental AG, a major German automotive parts manufacturer and tire producer.
-
E.
CON
CON is a Nigerian national honor post-nominal indicating a recipient of the Commander of the Order of the Niger.
- 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_69e245b0b01481908f636939bedd804c |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a751e6a08190a42c36722275d5d3 |
completed | April 29, 2026, 6:38 a.m. |
Created at: April 17, 2026, 6:03 p.m.