Triple
T3441331
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TalkTalk |
E72570
|
entity |
| Predicate | competitor |
P1375
|
FINISHED |
| Object | BT |
E241135
|
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 | Statement: [TalkTalk, competitor, BT]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: BT Context triple: [TalkTalk, competitor, BT]
-
A.
BT
BT is the vehicle registration code used on license plates for the city and district of Bayreuth in Upper Franconia, Germany.
-
B.
BT
BT is the two-letter ISO 3166-1 alpha-2 country code assigned to Bhutan for international standardization purposes.
-
C.
BT
chosen
BT is an American electronic music producer and composer known for pioneering trance and progressive electronic styles and for his innovative use of production techniques.
-
D.
Bt
Bt is the post-nominal abbreviation for a baronetcy title in the British honours system, indicating that the holder is a baronet.
-
E.
BAT
BAT is a major multinational tobacco company known for producing and marketing cigarettes and other nicotine products worldwide.
- 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_69ad85af50288190a854b76653deee6f |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adba276b708190949f294a8d09ec7b |
completed | March 8, 2026, 6:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b3548598088190907e13c88cb975fc |
completed | March 13, 2026, 12:04 a.m. |
Created at: March 8, 2026, 3:16 p.m.