Triple
T38298676
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eric Harris |
E1032162
|
entity |
| Predicate | createdContent |
P45409
|
FINISHED |
| Object | home videos with Dylan Klebold |
—
|
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: home videos with Dylan Klebold | Statement: [Eric Harris, createdContent, home videos with Dylan Klebold]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: createdContent Context triple: [Eric Harris, createdContent, home videos with Dylan Klebold]
-
A.
createdPost
Indicates that an entity authored or produced a specific post.
-
B.
createsContentAbout
Indicates that one entity produces or generates content whose subject or focus is another entity.
-
C.
createsContentFor
Indicates that one entity produces or generates content intended to be used by or directed toward another entity.
-
D.
createdWork
chosen
Indicates that an agent is responsible for bringing a work (such as a creative, intellectual, or produced artifact) into existence.
-
E.
creationType
Indicates the manner or process by which something was brought into existence or produced.
- 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_69f76e0f2084819091299d021625c3fe |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a000be59ad88190a6aa3a42c097796d |
completed | May 10, 2026, 4:39 a.m. |
| PD | Predicate disambiguation | batch_6a000ab6e9bc81908300b81d004e5921 |
completed | May 10, 2026, 4:33 a.m. |
Created at: May 3, 2026, 4:30 p.m.