Triple
T36717530
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | W. Mark Felt in Mank |
E906952
|
entity |
| Predicate | relatedRealEvent |
P93648
|
FINISHED |
| Object | Watergate investigation |
E1565
|
NE 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: Watergate investigation | Statement: [W. Mark Felt in Mank, relatedRealEvent, Watergate investigation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relatedRealEvent Context triple: [W. Mark Felt in Mank, relatedRealEvent, Watergate investigation]
-
A.
closelyAssociatedEvent
Indicates that one event is strongly related to, connected with, or occurs in close conjunction with another event.
-
B.
inspiredByRealEventType
Indicates that an event, action, or situation is based on, derived from, or influenced by an actual real-world occurrence.
-
C.
associatedEpicEvent
Indicates that one entity is linked or connected to a particular epic event in a relevant or meaningful way.
-
D.
significantEventInvolves
chosen
Indicates that a significant event includes or engages a particular entity as a participant or key element.
-
E.
relativeInvolvedInEvent
Indicates that a person’s relative participates in, is affected by, or is otherwise involved in a particular event.
- F. None of above.
Provenance (4 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_69f76e73ad108190a5241585f2303e9a |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a037c8e2c648190a65fc9c7872861af |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3a383578748190b64fa169172c6a90 |
completed | June 23, 2026, 7:39 a.m. |
| PD | Predicate disambiguation | batch_6a037a0e039481908a4a2666f76c5363 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:12 p.m.