Triple
T14376410
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | O2 |
E356485
|
entity |
| Predicate | formerName |
P65
|
FINISHED |
| Object | BT Cellnet |
E1095657
|
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: BT Cellnet | Statement: [O2, formerName, BT Cellnet]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: BT Cellnet Context triple: [O2, formerName, BT Cellnet]
-
A.
BT Cellnet
chosen
BT Cellnet was a major UK mobile phone network operator that later became part of the O2 brand.
-
B.
BTK
BTK (Bruton’s tyrosine kinase) is a key signaling enzyme in B cells and a major therapeutic target in certain blood cancers and autoimmune diseases.
-
C.
BTK
BTK is the ICAO airline designator assigned to Batik Air, an Indonesian full-service carrier.
-
D.
Betz cells
Betz cells are large, pyramidal neurons in the primary motor cortex that play a key role in voluntary motor control by sending long axons to the spinal cord.
-
E.
Netze
Netze is the German name for the Noteć, a river in north-central Poland that is a tributary of the Warta.
- 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_69d8279163a081908aec45c0e3f1e02f |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de900949fc81909be0da1734c46645 |
completed | April 14, 2026, 7:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd551002948190aeb93d245e1449a7 |
completed | May 8, 2026, 3:14 a.m. |
Created at: April 10, 2026, 1:16 a.m.