Triple
T5029603
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Seong Gi-hun |
E113262
|
entity |
| Predicate | endingStatus |
P13710
|
FINISHED |
| Object | traumatized by the experience |
—
|
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: traumatized by the experience | Statement: [Seong Gi-hun, endingStatus, traumatized by the experience]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: endingStatus Context triple: [Seong Gi-hun, endingStatus, traumatized by the experience]
-
A.
endingDescribedBy
Indicates that the conclusion or final part of something is characterized, explained, or detailed by a particular description or representation.
-
B.
endedWith
Indicates that one event, process, or state concluded with or was finalized by another specified event, condition, or outcome.
-
C.
losingState
Indicates that a particular game or competitive situation is in a condition where the player or side in question is currently losing or destined to lose under optimal play.
-
D.
laterStatus
chosen
Indicates that one entity represents a subsequent or resulting status or condition of another entity in time.
-
E.
status
Indicates the current condition, state, or standing of an entity within a given context.
- 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_69bd443775e48190a646ffbfc4334723 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd739099a0819099c6201d4e1c5ee2 |
completed | March 20, 2026, 4:19 p.m. |
| PD | Predicate disambiguation | batch_69bd71509e9c8190a60c1d8d04936a12 |
completed | March 20, 2026, 4:09 p.m. |
Created at: March 20, 2026, 1:36 p.m.