Triple
T28567001
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rostenkowski-Wolowitz |
E722705
|
entity |
| Predicate | usedInEpisodeContext |
P53947
|
FINISHED |
| Object | multiple episodes of The Big Bang Theory |
—
|
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: multiple episodes of The Big Bang Theory | Statement: [Rostenkowski-Wolowitz, usedInEpisodeContext, multiple episodes of The Big Bang Theory]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedInEpisodeContext Context triple: [Rostenkowski-Wolowitz, usedInEpisodeContext, multiple episodes of The Big Bang Theory]
-
A.
usedAsEpisodeReference
Indicates that one item is cited or employed as a reference point for a specific episode.
-
B.
usedInSeries
chosen
Indicates that something (such as an element, component, or concept) is employed or appears within a particular series.
-
C.
appearsInEpisodeType
Indicates that an entity is featured in, or associated with, a specific type or category of episode.
-
D.
usedInSeason
Indicates that something (such as an item, strategy, or element) is utilized or appears within a particular season.
-
E.
isKeyEpisodeIn
Indicates that an episode plays a crucial or defining role within a larger narrative, season, or series.
- 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_69f01a5f69d08190ad5c0d2167078dec |
completed | April 28, 2026, 2:24 a.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: April 28, 2026, 4:07 a.m.