Triple
T17238824
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary Mallon |
E418433
|
entity |
| Predicate | knownDeathsLinked |
P17673
|
FINISHED |
| Object | at least 3 deaths |
—
|
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: at least 3 deaths | Statement: [Mary Mallon, knownDeathsLinked, at least 3 deaths]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: knownDeathsLinked Context triple: [Mary Mallon, knownDeathsLinked, at least 3 deaths]
-
A.
notableDeath
Indicates that an entity’s death is considered significant or noteworthy in some context.
-
B.
causeOfDeathsCommemorated
Indicates that one entity is the cause of the deaths that are formally remembered or honored by another entity.
-
C.
associatedWithDeathOf
chosen
Indicates a relationship where one entity is connected in some relevant way to the death of another entity, such as by involvement, causation, or contextual association.
-
D.
causeOfDeath
Indicates the specific factor, event, or condition that directly resulted in an entity’s death.
-
E.
notableDeathTollEvent
Indicates that an event is characterized by causing an unusually large or historically significant number of deaths.
- 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_69d886d8e96081909870bff6c3d0bf09 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42dfdc8688190aceb223c19a48781 |
completed | April 19, 2026, 1:21 a.m. |
| PD | Predicate disambiguation | batch_69e3832553ac819091aa917c84f755b6 |
completed | April 18, 2026, 1:12 p.m. |
Created at: April 10, 2026, 5:39 a.m.