Triple
T26097816
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Katrina vanden Heuvel |
E658319
|
entity |
| Predicate | frequentGuestOn |
P127821
|
FINISHED |
| Object | U.S. television news programs |
—
|
LITERAL 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: U.S. television news programs | Statement: [Katrina vanden Heuvel, frequentGuestOn, U.S. television news programs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: frequentGuestOn Context triple: [Katrina vanden Heuvel, frequentGuestOn, U.S. television news programs]
-
A.
recurringGuestIn
chosen
Indicates that an entity appears repeatedly as a guest in a particular context, such as a show, event, or series.
-
B.
typicalGuests
Indicates the usual or most common guests associated with a particular host, place, or event.
-
C.
guestStar
Indicates that one entity appears in a limited, special, or featured role within another entity’s production, event, or context, without being a regular or primary participant.
-
D.
wasGuestHostOf
Indicates that one entity temporarily served as a guest host for another entity’s show, program, or event.
-
E.
notableOnAirPersonality
Indicates that an entity is recognized as a prominent or distinguished on-air media personality associated with another entity (such as a show, station, or network).
- F. None of above.
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_69ee5bc09c288190bc42a11972841383 |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69f627aedf548190bc9f53c8a2d67b50 |
completed | May 2, 2026, 4:34 p.m. |
| PD | Predicate disambiguation | batch_69f623a4e1048190bbb8dd1253fdcee9 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 26, 2026, 7:52 p.m.