Triple
T33121622
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Through the Looking Glass (Lost) |
E847615
|
entity |
| Predicate | basedOnTitleAuthor |
P2806
|
FINISHED |
| Object | Lewis Carroll |
—
|
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: Lewis Carroll | Statement: [Through the Looking Glass (Lost), basedOnTitleAuthor, Lewis Carroll]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: basedOnTitleAuthor Context triple: [Through the Looking Glass (Lost), basedOnTitleAuthor, Lewis Carroll]
-
A.
basedOnAuthor
chosen
Indicates that one entity is derived from, inspired by, or otherwise created on the basis of the work or contributions of a particular author.
-
B.
originalTitleAuthorName
Indicates that the associated name is the author of the work’s original title.
-
C.
titleBasedIn
Indicates that a creative work’s title is derived from, inspired by, or directly taken from a particular source or context.
-
D.
basedOnAuthorCollaboratedWith
Indicates that one entity is derived from, influenced by, or created using work that was produced through a collaboration between the specified author and another contributor.
-
E.
authorTitle
Indicates that a person is the creator or writer of a work that bears the specified title.
- 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_69f349588f088190b7c9588860f72033 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fe9dfaa2d08190b2084f63f842eb6b |
completed | May 9, 2026, 2:37 a.m. |
| PD | Predicate disambiguation | batch_69fe9bba947c81908b0b2b92a4d19b37 |
completed | May 9, 2026, 2:28 a.m. |
Created at: May 1, 2026, 1:27 a.m.