Triple
T25210926
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Archibald Bunker |
E631681
|
entity |
| Predicate | inUniverseHobby |
P158422
|
FINISHED |
| Object | watching television |
—
|
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: watching television | Statement: [Archibald Bunker, inUniverseHobby, watching television]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inUniverseHobby Context triple: [Archibald Bunker, inUniverseHobby, watching television]
-
A.
inUniverse
Indicates that one entity exists, occurs, or is set within the fictional or conceptual universe defined by another entity.
-
B.
inUniverseContribution
Indicates that an entity contributes content, events, or elements that exist within the fictional universe or canon of another entity.
-
C.
inUniverseUse
Indicates that something is used or occurs within a particular fictional or conceptual universe, as opposed to in the real world or another setting.
-
D.
inUniverseTheme
Indicates that a theme or motif exists within and is relevant to the internal, fictional universe of a work, as opposed to being purely meta or external.
-
E.
inUniverseSpeaker
Indicates that the subject is a speaker or narrator who exists within the fictional universe or narrative world being described.
- F. None of above. chosen
Provenance (4 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_69e75a8d1aa48190a4320acd3654762c |
completed | April 21, 2026, 11:07 a.m. |
| NER | Named-entity recognition | batch_69f47b8918fc819080825ed92fb3a1a7 |
completed | May 1, 2026, 10:08 a.m. |
| PD | Predicate disambiguation | batch_69f4683472ec8190a483b3b8afe71720 |
completed | May 1, 2026, 8:45 a.m. |
| PDg | Predicate description generation | batch_69f46d361c348190b5fdfd805ecde01b |
completed | May 1, 2026, 9:07 a.m. |
Created at: April 21, 2026, 12:58 p.m.