Triple
T19687821
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary Dedalus |
E472756
|
entity |
| Predicate | deathStatusInUlysses |
P24966
|
FINISHED |
| Object | deceased |
—
|
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: deceased | Statement: [Mary Dedalus, deathStatusInUlysses, deceased]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: deathStatusInUlysses Context triple: [Mary Dedalus, deathStatusInUlysses, deceased]
-
A.
deathStatus
chosen
Indicates whether an entity is alive, dead, or in another specified state related to mortality.
-
B.
deathOutcome
Indicates that an event, condition, or action results in the death of the affected entity.
-
C.
deathDescribedIn
Indicates that a person's death is documented, narrated, or otherwise detailed within a particular source or description.
-
D.
deathInterpretedAs
Indicates that one entity’s death is understood, framed, or interpreted in a particular way by another entity or within a given context.
-
E.
deathOvers
Indicates the number of overs bowled in the final phase of a limited-overs cricket innings, typically focused on the closing overs where scoring and wicket-taking intensify.
- 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_69d8e515bef88190bc30781aea50537a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6420d39688190ad3a84dbffce4ffe |
completed | April 20, 2026, 3:11 p.m. |
| PD | Predicate disambiguation | batch_69e53039ea808190a9106a53f564ab92 |
completed | April 19, 2026, 7:42 p.m. |
Created at: April 10, 2026, 1:45 p.m.