Triple
T30459160
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oprah’s Master Class |
E774948
|
entity |
| Predicate | featuresGuest |
P45889
|
FINISHED |
| Object | Maya Angelou |
—
|
NE NERFINISHED |
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: Maya Angelou | Statement: [Oprah’s Master Class, featuresGuest, Maya Angelou]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresGuest Context triple: [Oprah’s Master Class, featuresGuest, Maya Angelou]
-
A.
featuresGuestContributions
Indicates that an entity includes or showcases content, work, or input provided by external guests rather than its primary or regular contributors.
-
B.
guestStar
chosen
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.
-
C.
featuresPeople
Indicates that something prominently includes or showcases specific people as part of its content or presentation.
-
D.
typicalGuests
Indicates the usual or most common guests associated with a particular host, place, or event.
-
E.
guestOnBoard
Indicates that an entity is currently present as a guest aboard a vehicle, vessel, or similar conveyance.
- 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_69f22494fb60819095d893de0284f886 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_6a000014497c819088d5cda3977522dd |
completed | May 10, 2026, 3:48 a.m. |
| PD | Predicate disambiguation | batch_69ffff9a52b08190be1024e0fb6fe661 |
completed | May 10, 2026, 3:46 a.m. |
Created at: April 29, 2026, 8:10 p.m.