Triple
T33349517
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BBC (song) |
E853893
|
entity |
| Predicate | inUniversePerformer |
P46922
|
FINISHED |
| Object | Ming Tea |
—
|
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: Ming Tea | Statement: [BBC (song), inUniversePerformer, Ming Tea]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inUniversePerformer Context triple: [BBC (song), inUniversePerformer, Ming Tea]
-
A.
inUniverseCharacter
Indicates that a character exists within, and is part of, the fictional universe or continuity defined by a particular work or franchise.
-
B.
inUniverseActor
Indicates that an actor or character exists and operates within a specified fictional universe or narrative world.
-
C.
inUniverseSpeaker
Indicates that the subject is a speaker or narrator who exists within the fictional universe or narrative world being described.
-
D.
coPerformer
chosen
Indicates that two or more entities jointly perform the same act or participate together in the same performance.
-
E.
inUniverseManagerPortrayedBy
Indicates that a fictional in-universe manager character is portrayed by a particular real-world performer or actor.
- 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_69f3496a1a588190bad9cbe9221144e0 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7979a073881909a4fde2558e6b6f3 |
completed | May 3, 2026, 6:44 p.m. |
| PD | Predicate disambiguation | batch_69f7961550f88190b7bb8a9155458b54 |
completed | May 3, 2026, 6:38 p.m. |
Created at: May 1, 2026, 1:34 a.m.