Triple
T33712478
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gordon the Big Engine |
E863777
|
entity |
| Predicate | authorOfFirstAppearance |
P192352
|
FINISHED |
| Object | Rev. W. Awdry |
—
|
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: Rev. W. Awdry | Statement: [Gordon the Big Engine, authorOfFirstAppearance, Rev. W. Awdry]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: authorOfFirstAppearance Context triple: [Gordon the Big Engine, authorOfFirstAppearance, Rev. W. Awdry]
-
A.
directorOfFirstAppearance
Indicates that a person is the director responsible for an entity’s first appearance (e.g., first episode, film, or installment) in a series or franchise.
-
B.
firstAppearancePublisher
Indicates the publisher responsible for releasing an entity’s first appearance.
-
C.
firstAppearanceCreator
chosen
Indicates that an entity is the creator responsible for the first appearance or original introduction of another entity.
-
D.
airDateOfFirstAppearance
Indicates the calendar date on which an entity (such as a character, show, or episode) was first broadcast or made publicly available.
-
E.
firstAppearanceInComicsIssue
Indicates the specific comic book issue in which an entity (such as a character or item) is depicted for the first time.
- 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_69f3498844608190bb8f9b14908d2510 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fd7b0503a08190ba07338365b6fcc9 |
completed | May 8, 2026, 5:56 a.m. |
| PD | Predicate disambiguation | batch_69fd7a9733dc81909199f453c0cc2bc1 |
completed | May 8, 2026, 5:54 a.m. |
Created at: May 1, 2026, 1:43 a.m.