Triple
T33121621
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Through the Looking Glass (Lost) |
E847615
|
entity |
| Predicate | basedOnTitleReference |
P99044
|
FINISHED |
| Object | Through the Looking-Glass |
—
|
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: Through the Looking-Glass | Statement: [Through the Looking Glass (Lost), basedOnTitleReference, Through the Looking-Glass]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: basedOnTitleReference Context triple: [Through the Looking Glass (Lost), basedOnTitleReference, Through the Looking-Glass]
-
A.
titleBasedIn
Indicates that a creative work’s title is derived from, inspired by, or directly taken from a particular source or context.
-
B.
canonicalReferenceTitle
Indicates that one entity serves as the standard or authoritative title by which another entity is formally referenced or identified.
-
C.
refersToTitleHolder
Indicates that one entity makes reference to, or designates, the entity that currently holds a specific title or position.
-
D.
basedOnText
Indicates that something is derived, adapted, or developed from a specific text source.
-
E.
titleBasis
chosen
Indicates that one entity serves as the basis or source material for the title or name of another entity.
- 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_69fe9b0276d48190b554fa22b043e6d8 |
completed | May 9, 2026, 2:25 a.m. |
| PD | Predicate disambiguation | batch_69fe999692b081909921e1148d66f0ef |
completed | May 9, 2026, 2:19 a.m. |
Created at: May 1, 2026, 1:27 a.m.