Triple
T33462094
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Joseph Rouletabille series |
E856945
|
entity |
| Predicate | hasTypeOfMystery |
P166129
|
FINISHED |
| Object | locked-room mystery |
—
|
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: locked-room mystery | Statement: [Joseph Rouletabille series, hasTypeOfMystery, locked-room mystery]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTypeOfMystery Context triple: [Joseph Rouletabille series, hasTypeOfMystery, locked-room mystery]
-
A.
hasMystery
Indicates that one entity possesses, contains, or is associated with something unknown, secret, or unexplained in relation to another entity.
-
B.
hasMysteryType
chosen
Indicates that an entity is associated with, categorized under, or characterized by a particular type whose nature or classification is unknown, hidden, or unspecified.
-
C.
mysteryAssociatedWith
Indicates a relationship where something is connected to, involved in, or characterized by an element of mystery or the unknown.
-
D.
mysterySet
Indicates that an entity belongs to a collection or group whose nature, contents, or defining criteria are unknown or intentionally unspecified.
-
E.
containsMurderMystery
Indicates that one entity (such as a work or collection) includes or features a murder mystery as part of its content.
- 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_69f34973461481909c701c98ebd75623 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69ff0b6bc4a88190bf1d38c6ea26bcdc |
completed | May 9, 2026, 10:24 a.m. |
| PD | Predicate disambiguation | batch_69ff082a22f4819095ded971dbd8ea7b |
completed | May 9, 2026, 10:10 a.m. |
Created at: May 1, 2026, 1:37 a.m.