Triple
T27817502
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Mystery of Edwin Drood |
E702714
|
entity |
| Predicate | hasUnresolvedPlot |
P42590
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [The Mystery of Edwin Drood, hasUnresolvedPlot, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasUnresolvedPlot Context triple: [The Mystery of Edwin Drood, hasUnresolvedPlot, true]
-
A.
hasPlot
Indicates that an entity (such as a narrative work) possesses or is associated with a specific storyline or sequence of events.
-
B.
hasMainPlotElement
Indicates that one entity serves as a central or primary plot element within the narrative of another entity.
-
C.
hasMinimalPlot
Indicates that a work’s storyline is very simple, sparse, or lacking in substantial narrative development.
-
D.
hasUnfinishedEnding
chosen
Indicates that an entity concludes in an incomplete, unresolved, or open-ended manner rather than reaching a fully finished state.
-
E.
notResolvedBy
Indicates that an issue, problem, or request remains unresolved despite the involvement or actions of a specified 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_69ef840ad1e88190b5bff2d1ddec8700 |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_69f6978fe97081908fe568091ad9b159 |
completed | May 3, 2026, 12:32 a.m. |
| PD | Predicate disambiguation | batch_69f69661e6ec8190948251c7516a32ad |
completed | May 3, 2026, 12:27 a.m. |
Created at: April 27, 2026, 5:46 p.m.