Triple
T1556719
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bernadine Harris |
E33220
|
entity |
| Predicate | undergoesEvent |
P17155
|
FINISHED |
| Object | divorce from John Harris |
—
|
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: divorce from John Harris | Statement: [Bernadine Harris, undergoesEvent, divorce from John Harris]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: undergoesEvent Context triple: [Bernadine Harris, undergoesEvent, divorce from John Harris]
-
A.
dealtWithEvent
Indicates that an entity has handled, responded to, or otherwise taken action to address a particular event.
-
B.
interpretsEvent
Indicates that an entity analyzes and assigns meaning or significance to an event.
-
C.
parentEvent
Indicates that one event serves as the higher-level or originating event from which another event is derived, contained, or logically dependent.
-
D.
facedEvent
chosen
Indicates that an entity directly encountered, experienced, or dealt with a particular event.
-
E.
triggerEvent
Indicates that one entity causes or initiates the occurrence of a specific event involving another entity or the system.
- 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_69a885ef9cf48190b0af0f5ce3d02231 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a9407d9d1481909597af97b16512cc |
completed | March 5, 2026, 8:36 a.m. |
| PD | Predicate disambiguation | batch_69a907b688d081908171f89010c53973 |
completed | March 5, 2026, 4:33 a.m. |
Created at: March 4, 2026, 7:27 p.m.