Triple
T21039796
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Sinatra as Major Bennett Marco |
E518289
|
entity |
| Predicate | characterPsychologicalState |
P113325
|
FINISHED |
| Object | suffers from nightmares |
—
|
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: suffers from nightmares | Statement: [Frank Sinatra as Major Bennett Marco, characterPsychologicalState, suffers from nightmares]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: characterPsychologicalState Context triple: [Frank Sinatra as Major Bennett Marco, characterPsychologicalState, suffers from nightmares]
-
A.
성격
Indicates a relationship where one entity’s character, temperament, or personality traits are attributed to or associated with that entity.
-
B.
psychologicalStateAfterCrime
Indicates the mental or emotional condition an individual experiences as a consequence of committing a crime.
-
C.
personalityType
Indicates the specific psychological or behavioral profile that characterizes an entity’s typical patterns of thinking, feeling, and acting.
-
D.
mentalStateChange
Indicates a change in an entity’s mental or emotional condition from one state to another.
-
E.
hasPsychologicalCondition
chosen
Indicates that an entity experiences or is diagnosed with a particular psychological or mental health condition.
- 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_69e0b50438e08190917e2538bb8bc034 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fceed9148190903adb3b55f65242 |
completed | April 21, 2026, 4:28 a.m. |
| PD | Predicate disambiguation | batch_69e5dbf6728881908a2a43a5c8804a2a |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 16, 2026, 2:14 p.m.