Triple
T14551970
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Margaret Thatcher in The Crown |
E341439
|
entity |
| Predicate | lastAppearanceSeason |
P16814
|
FINISHED |
| Object | season 4 of The Crown |
—
|
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: season 4 of The Crown | Statement: [Margaret Thatcher in The Crown, lastAppearanceSeason, season 4 of The Crown]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lastAppearanceSeason Context triple: [Margaret Thatcher in The Crown, lastAppearanceSeason, season 4 of The Crown]
-
A.
lastCompletedSeason
Indicates the most recent season of an ongoing or episodic series that has been fully finished or concluded.
-
B.
lastWorksSeason
Indicates the season in which an entity (such as a person or organization) last performed work or was active in a particular role or context.
-
C.
lastAppearance
chosen
Indicates the most recent time or instance in which an entity appears or is present within a given context or sequence.
-
D.
lastRegularAppearanceDate
Indicates the date on which an entity made its most recent standard or non-special appearance.
-
E.
seasonAppearance
Indicates that an entity appears in, or is present during, a particular season within a series or sequence.
- 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_69d822db9c8481908213ceb39585f792 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb2ee34208190bf040a513767c958 |
completed | April 14, 2026, 9:34 p.m. |
| PD | Predicate disambiguation | batch_69de5c546c7081909e27d504ec360c5c |
completed | April 14, 2026, 3:25 p.m. |
Created at: April 10, 2026, 1:23 a.m.