Triple
T30427241
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Adventure of the Dying Detective |
E774066
|
entity |
| Predicate | culminatingEvent |
P82427
|
FINISHED |
| Object | Culverton Smith’s confession |
—
|
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: Culverton Smith’s confession | Statement: [The Adventure of the Dying Detective, culminatingEvent, Culverton Smith’s confession]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: culminatingEvent Context triple: [The Adventure of the Dying Detective, culminatingEvent, Culverton Smith’s confession]
-
A.
isCulminatingEventOf
chosen
Indicates that an event represents the final or peak outcome within a larger process, sequence, or series of related events.
-
B.
finalOccasion
Indicates that an event or occurrence is the last or concluding instance in a sequence or series.
-
C.
celebratedEvent
Indicates that an entity has been honored, commemorated, or festively observed as a special event.
-
D.
climaxEvents
Indicates that the related events represent the peak or most intense turning point within a larger sequence or narrative.
-
E.
significantEventEnd
Indicates the point in time when a significant event or occurrence comes to a close or is considered finished.
- 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_69f22491ba248190b9a4776ca8e42d02 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6866990548190aea96f3a46ba2e43 |
completed | May 2, 2026, 11:19 p.m. |
| PD | Predicate disambiguation | batch_69f678d2196c8190b9d0d2fcd47cc539 |
completed | May 2, 2026, 10:21 p.m. |
Created at: April 29, 2026, 8:06 p.m.