Triple
T17260315
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tanya Donelly |
E418990
|
entity |
| Predicate | recordLabel |
P1500
|
FINISHED |
| Object | 4AD |
E198312
|
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: 4AD | Statement: [Tanya Donelly, recordLabel, 4AD]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 4AD Context triple: [Tanya Donelly, recordLabel, 4AD]
-
A.
4AD
chosen
4AD is a British independent record label known for its influential roster of alternative and indie artists and its distinctive visual and sonic aesthetic.
-
B.
4BC
4BC is a Brisbane-based commercial talk radio station in Australia, known for its news, talkback, and sports programming.
-
C.
Wusi Dajie
Wusi Dajie is a major street in central Beijing known for its cultural institutions and proximity to key historical and political landmarks.
-
D.
Taikon
Taikon is a Romani Swedish family name most prominently associated with activist and silversmith Rosa Taikon and her relatives.
-
E.
Tadian
Tadian is a rural municipality in the Cordillera region of the Philippines known for its mountainous terrain, indigenous Kankanaey culture, and terraced agricultural landscapes.
- 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_69d886d9ab108190b70edd8d17aa1204 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42e6fa940819089046d1b12dede2c |
completed | April 19, 2026, 1:22 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0179445cac8190833eb7cd879a93bd |
completed | May 11, 2026, 6:37 a.m. |
Created at: April 10, 2026, 5:39 a.m.