Triple
T108792
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NBC |
E2196
|
entity |
| Predicate | majorCompetitor |
P1794
|
FINISHED |
| Object | CBS |
E6070
|
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: CBS | Statement: [NBC, majorCompetitor, CBS]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: CBS Context triple: [NBC, majorCompetitor, CBS]
-
A.
CBS
chosen
CBS is a major American broadcast television network known for airing a wide range of popular news, sports, and entertainment programming nationwide.
-
B.
NBC
NBC is a major American broadcast television network known for its nationwide programming, including news, sports, and entertainment.
-
C.
PBS
PBS is a U.S. public television network known for educational, scientific, and cultural programming.
-
D.
NBCUniversal
NBCUniversal is a major American media and entertainment conglomerate known for its television networks, film studio, and extensive sports broadcasting portfolio.
-
E.
CBC
CBC is Canada's national public broadcaster, known for airing major sports events, news, and original programming on television and radio.
- 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_69a24fcdaeb48190a2d796677e4b3281 |
completed | Feb. 28, 2026, 2:15 a.m. |
| NER | Named-entity recognition | batch_69a25b7e2c188190b1dd8aafd4507a99 |
completed | Feb. 28, 2026, 3:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a2b01662f88190a4997a3e86c17946 |
completed | Feb. 28, 2026, 9:06 a.m. |
Created at: Feb. 28, 2026, 2:20 a.m.