Triple
T11344252
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sally Draper |
E268676
|
entity |
| Predicate | witnessesEvent |
P56735
|
FINISHED |
| Object | parents’ marital conflicts |
—
|
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: parents’ marital conflicts | Statement: [Sally Draper, witnessesEvent, parents’ marital conflicts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: witnessesEvent Context triple: [Sally Draper, witnessesEvent, parents’ marital conflicts]
-
A.
witnesses
chosen
Indicates that one entity observes an event, action, or situation involving another entity, typically as a bystander or observer.
-
B.
historicalEventWitnessed
Indicates that an entity personally observed or was present at a particular historical event.
-
C.
notableWitness
Indicates that one entity is a significant or prominent witness to an event, action, or situation involving another entity.
-
D.
numberOfWitnessesHeard
Indicates the count of witnesses whose testimony or statements were heard in a given event or proceeding.
-
E.
participatedInEvent
Indicates that an entity took part in or was actively involved in a specific event.
- 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_69d6aacbe18081909e5fadb50082dd96 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d80148e2048190a716b515d78efdd1 |
completed | April 9, 2026, 7:43 p.m. |
| PD | Predicate disambiguation | batch_69d7e6f8aeb4819080476f16a69b2ee3 |
completed | April 9, 2026, 5:50 p.m. |
Created at: April 8, 2026, 9:33 p.m.