Triple
T26901633
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary Morstan |
E678044
|
entity |
| Predicate | centralMysteryIn |
P25900
|
FINISHED |
| Object | The Sign of Four |
—
|
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: The Sign of Four | Statement: [Mary Morstan, centralMysteryIn, The Sign of Four]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: centralMysteryIn Context triple: [Mary Morstan, centralMysteryIn, The Sign of Four]
-
A.
centralMystery
chosen
Indicates that something serves as the primary unresolved question or puzzle around which a narrative, situation, or investigation is structured.
-
B.
centralConjecture
Indicates that the subject proposition is the main or most important conjecture around which related arguments, results, or discussions are organized.
-
C.
centralIn
Indicates that one entity occupies a central or most important position within another entity, context, or structure.
-
D.
secondMystery
Indicates a secondary, less obvious or more enigmatic relationship or phenomenon whose nature is not immediately clear or explicitly defined.
-
E.
focusesOnMysteries
Indicates that the subject concentrates attention or effort specifically on mysteries, such as puzzling events, unknown phenomena, or unsolved cases.
- 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_69eee9befee48190a26f214faa867be7 |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69f6afebd7ec8190ab696f363d84abf0 |
completed | May 3, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69f6aca204148190850a3dc325bc07b7 |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 27, 2026, 5:51 a.m.