Triple
T16084521
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cox Communications |
E390193
|
entity |
| Predicate | brandName |
P1500
|
FINISHED |
| Object | Cox |
E14655
|
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: Cox | Statement: [Cox Communications, brandName, Cox]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cox Context triple: [Cox Communications, brandName, Cox]
-
A.
Cox
Cox is a common English surname of British and Irish origin, borne by numerous notable figures across politics, law, entertainment, and sports.
-
B.
Paxson
Paxson is a small unincorporated community in Alaska known as a remote junction and stopping point for travelers in the state's interior.
-
C.
Cox Enterprises
chosen
Cox Enterprises is a major U.S. privately held media, communications, and automotive services conglomerate.
-
D.
Cocke
Cocke is an English-language surname borne by various notable figures in American political and military history.
-
E.
Cockrel
Cockrel is a surname most notably associated with Detroit politician and former mayor Kenneth Cockrel Jr.
- 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_69d87f198bc48190a8b7e53ca15b7ead |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e1844d7d688190b5badac7a8014f89 |
completed | April 17, 2026, 12:52 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffe48ef3608190848d4730a4361395 |
completed | May 10, 2026, 1:51 a.m. |
Created at: April 10, 2026, 4:59 a.m.