Triple
T37529599
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Kramer |
E932993
|
entity |
| Predicate | killsIndirectly |
P77493
|
FINISHED |
| Object | victims who fail his tests |
—
|
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: victims who fail his tests | Statement: [John Kramer, killsIndirectly, victims who fail his tests]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: killsIndirectly Context triple: [John Kramer, killsIndirectly, victims who fail his tests]
-
A.
killsAt
Indicates that one entity causes the death of another entity at a specific time or event.
-
B.
killsByProxy
chosen
Indicates that one entity causes the death of another entity indirectly through an intermediary or agent rather than committing the act personally.
-
C.
kills
Indicates that one entity causes the death of another entity, ending its life.
-
D.
skillUsedFor
Indicates that a particular skill is employed or applied to perform, achieve, or facilitate a specific task, goal, or function.
-
E.
skilledIn
Indicates that an entity possesses ability, expertise, or proficiency in performing or using another entity (such as a task, tool, or domain).
- 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_69f76ec8862c8190bfa24145f5480642 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fba5eec0448190a5e6f0c43fdcd0e3 |
completed | May 6, 2026, 8:34 p.m. |
| PD | Predicate disambiguation | batch_69fba34edd548190bfa980e6e16e0a88 |
completed | May 6, 2026, 8:23 p.m. |
Created at: May 3, 2026, 4:17 p.m.