Triple
T34955789
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Evil manual |
E1008119
|
entity |
| Predicate | documentationFor |
P132738
|
FINISHED |
| Object | Evil package |
—
|
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: Evil package | Statement: [Evil manual, documentationFor, Evil package]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: documentationFor Context triple: [Evil manual, documentationFor, Evil package]
-
A.
documentationReference
chosen
Indicates that one entity serves as a documentation source or reference that explains, specifies, or supports another entity.
-
B.
documentationUI
Indicates a relationship where a user interface element is used to present, navigate, or interact with documentation content.
-
C.
documentedUsing
Indicates that something is recorded, described, or specified by means of a particular document, tool, or documentation method.
-
D.
documentationShownIn
Indicates that certain documentation is displayed or made visible within a particular context, interface, or location.
-
E.
documentationSection
Indicates that one entity is a specific section or subdivision within the documentation of 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_69f76dc69564819099e9e78aed6ff0a6 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f78fd5a6388190bfda4bbb2e222e5b |
completed | May 3, 2026, 6:11 p.m. |
| PD | Predicate disambiguation | batch_69f78e2ac3fc819081a45c6841375c8d |
completed | May 3, 2026, 6:04 p.m. |
Created at: May 3, 2026, 4 p.m.