Triple
T20444270
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dave Holland |
E501474
|
entity |
| Predicate | recordLabel |
P1500
|
FINISHED |
| Object | ECM |
—
|
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: ECM | Statement: [Dave Holland, recordLabel, ECM]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ECM Context triple: [Dave Holland, recordLabel, ECM]
-
A.
ECM
ECM is a financial forecasting model developed by economist Martin Armstrong that predicts economic cycles and market turning points based on a recurring time interval.
-
B.
EC-M
EC-M is the vehicle registration and regional code assigned to the Macas area in Ecuador.
-
C.
ECM New Series
chosen
ECM New Series is a renowned classical and contemporary music imprint of the ECM record label, known for its high-quality recordings, innovative repertoire, and distinctive sound aesthetic.
-
D.
ECUM
ECUM is the School of Sciences at the University of Minho, a Portuguese higher education institution focused on scientific education and research.
-
E.
EMCC
EMCC is a public community college in Bangor, Maine, offering two-year degree and certificate programs focused on career and technical education.
- 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_69e0b4ac0a1c81908845d0f8a56abce8 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e68cfca4788190ad57ecb504f54d11 |
completed | April 20, 2026, 8:30 p.m. |
Created at: April 16, 2026, 11:32 a.m.