Triple

T10751435
Position Surface form Disambiguated ID Type / Status
Subject WGN-TV E253579 entity
Predicate formerSuperstationFeed P95785 FINISHED
Object WGN America E98192 NE FINISHED

How this triple was built (3 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: WGN America | Statement: [WGN-TV, formerSuperstationFeed, WGN America]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: WGN America
Context triple: [WGN-TV, formerSuperstationFeed, WGN America]
  • A. WGN America chosen
    WGN America is a U.S.-based cable television network known for airing syndicated series, movies, and original programming to a national audience.
  • B. WGN-TV
    WGN-TV is a Chicago-based television station and former national superstation known for its local news, sports broadcasts, and syndicated programming.
  • C. WGN
    WGN is the National Rail station code for Wigan North Western railway station in Greater Manchester, England.
  • D. WGN Radio
    WGN Radio is a historic Chicago-based AM radio station known for its news, talk, and sports programming and long association with the Chicago Tribune.
  • E. CW Network
    The CW Network is an American broadcast television network known for airing youth-oriented series, superhero shows, and teen dramas.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: formerSuperstationFeed
Context triple: [WGN-TV, formerSuperstationFeed, WGN America]
  • A. feedsCanal
    Indicates that one water source supplies or channels water into a canal.
  • B. feedsReservoir
    Indicates that one entity supplies or channels a flow (such as water or another resource) into a reservoir.
  • C. feedsOn
    Indicates that one entity obtains nourishment by consuming another entity as food.
  • D. feedsAccelerator
    Indicates that one entity supplies or directs input, resources, or power into an accelerator system for its operation.
  • E. feedsAt
    Indicates that one entity obtains or consumes food at, from, or using another entity (such as a location, source, or feeding apparatus).
  • F. None of above. chosen

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_69d6aa5e51e8819095f06881cecf152e completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d71dc0ad188190b747bf9d10cf5de5 completed April 9, 2026, 3:32 a.m.
NED1 Entity disambiguation (via context triple) batch_69de23292f8c8190a52c94c03e7d476d completed April 14, 2026, 11:21 a.m.
PD Predicate disambiguation batch_69d6f30df9948190ab3cdc33977fac14 completed April 9, 2026, 12:30 a.m.
PDg Predicate description generation batch_69d6fa323564819097b207eb53f8a9b8 completed April 9, 2026, 1 a.m.
Created at: April 8, 2026, 9:15 p.m.