Triple
T35864244
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lydia Glasher |
E1037037
|
entity |
| Predicate | hasFoilRelationshipWith |
P42265
|
FINISHED |
| Object | Gwendolen Harleth |
—
|
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: Gwendolen Harleth | Statement: [Lydia Glasher, hasFoilRelationshipWith, Gwendolen Harleth]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFoilRelationshipWith Context triple: [Lydia Glasher, hasFoilRelationshipWith, Gwendolen Harleth]
-
A.
hasFoilOrParallel
Indicates that one item is a foil or parallel version of another, typically differing only in special variant features while representing the same underlying entity.
-
B.
isFoiledBy
Indicates that an action, plan, or attempt is prevented, blocked, or rendered unsuccessful by another entity or event.
-
C.
hasFoilCharacters
chosen
Indicates that one character is contrasted with another to highlight their differing traits, qualities, or roles.
-
D.
isSupercardOf
Indicates that one card or set of cards fully contains or extends the content, scope, or functionality of another card, making it a more comprehensive or encompassing version.
-
E.
isCollectibleFigure
Indicates that an entity is a figure or model intended primarily for collection rather than ordinary use or play.
- 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_69f76e1d279c8190843e5b64a0a12c3f |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fe744faca881908e11e90e0a35653f |
completed | May 8, 2026, 11:39 p.m. |
| PD | Predicate disambiguation | batch_69fe734cbf7081909a552c5cf3b5ea59 |
completed | May 8, 2026, 11:35 p.m. |
Created at: May 3, 2026, 4:06 p.m.