Triple

T33955818
Position Surface form Disambiguated ID Type / Status
Subject CN8 E870568 entity
Predicate alsoKnownAs P39 FINISHED
Object Comcast Network 8
Comcast Network 8 is a regional American cable television channel formerly branded as CN8, known for offering local news, sports, and community programming to Comcast subscribers.
E13233 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: Comcast Network 8 | Statement: [CN8, alsoKnownAs, Comcast Network 8]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Comcast Network 8
Triple: [CN8, alsoKnownAs, Comcast Network 8]
Generated description
Comcast Network 8 is a regional American cable television channel formerly branded as CN8, known for offering local news, sports, and community programming to Comcast subscribers.

Provenance (5 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_69f3499c2d7481909c953a5010227725 completed April 30, 2026, 12:22 p.m.
NER Named-entity recognition batch_69f702b9585c8190b538c9974de3fee8 completed May 3, 2026, 8:09 a.m.
NED1 Entity disambiguation (via context triple) batch_6a3689e1936c81908bda86bb57edc7cc completed June 20, 2026, 12:38 p.m.
NEDg Description generation batch_6a368a5fb37c8190a2576c9cae8dfe19 completed June 20, 2026, 12:41 p.m.
NED2 Entity disambiguation (via description) batch_6a368e2e589881909e91cdb35205bc51 completed June 20, 2026, 12:57 p.m.
Created at: May 1, 2026, 1:49 a.m.