Triple
T19090361
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lee Adama |
E467264
|
entity |
| Predicate | guiltOver |
P62179
|
FINISHED |
| Object | death of Zak Adama |
—
|
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: death of Zak Adama | Statement: [Lee Adama, guiltOver, death of Zak Adama]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: guiltOver Context triple: [Lee Adama, guiltOver, death of Zak Adama]
-
A.
guiltyOf
Indicates that an entity has been judged or determined to have committed a particular offense, crime, or wrongful act.
-
B.
repentsFor
Indicates that one entity feels remorse or regret for an action, wrongdoing, or harm related to another entity.
-
C.
contritionType
Indicates the specific kind or category of contrition (remorse or repentance) associated with an action or state.
-
D.
repentedIn
Indicates that an entity has expressed remorse or regret for its actions within a particular context, time, or situation.
-
E.
laterRegretted
chosen
Indicates that an entity experienced regret at a later time about a prior action, decision, or state involving another entity.
- 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_69d8dd05ac4c8190b1967d8f97f3fb2f |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e34a589c8190b5171fab45bf2204 |
completed | April 20, 2026, 8:26 a.m. |
| PD | Predicate disambiguation | batch_69e4b9a604308190a3235184f9f2c056 |
completed | April 19, 2026, 11:16 a.m. |
Created at: April 10, 2026, 12:04 p.m.