Triple
T21842434
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Detective Richard Willis |
E539286
|
entity |
| Predicate | firstTVAppearanceYear |
P121574
|
FINISHED |
| Object | 2018 |
—
|
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: 2018 | Statement: [Detective Richard Willis, firstTVAppearanceYear, 2018]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstTVAppearanceYear Context triple: [Detective Richard Willis, firstTVAppearanceYear, 2018]
-
A.
firstPublicationYearOfAppearance
Indicates the year in which an entity (such as a work or character) first appeared in a published form.
-
B.
firstAppearanceTV
Indicates the television show or episode in which an entity is depicted or mentioned for the first time.
-
C.
firstAppearedAt
Indicates the point in time or specific event at which an entity was first introduced, observed, or became known.
-
D.
firstPopularAppearance
Indicates the earliest notable or widely recognized appearance of an entity in a public or popular context.
-
E.
yearOfFirstApparition
chosen
Indicates the calendar year in which the entity first appeared or was introduced.
- 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_69e0c476c3c88190a92d08ebb59a128a |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f0a7ad76d48190a1905cfdbe866323 |
completed | April 28, 2026, 12:27 p.m. |
| PD | Predicate disambiguation | batch_69e6be8c14748190bdcc44a14d50bea4 |
completed | April 21, 2026, 12:02 a.m. |
Created at: April 16, 2026, 6:55 p.m.