Triple
T18015970
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NumFOCUS |
E430998
|
entity |
| Predicate | supportsProject |
P12986
|
FINISHED |
| Object | Bokeh |
—
|
NE NERFINISHED |
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: Bokeh | Statement: [NumFOCUS, supportsProject, Bokeh]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bokeh Context triple: [NumFOCUS, supportsProject, Bokeh]
-
A.
Bokeh
chosen
Bokeh is an interactive visualization library for Python that enables the creation of rich, web-ready plots and dashboards from large or streaming datasets.
-
B.
Aperture
Aperture was Apple’s professional photo editing and management application for macOS, aimed at photographers needing advanced workflow and image processing tools.
-
C.
Pincushion
"Pincushion" is a 1994 blues-rock song by American rock band ZZ Top, known for its gritty guitar riffs and appearance on their album *Antenna*.
-
D.
Into the Lens
Into the Lens is a progressive rock song by the English band Yes, originally appearing on their 1980 album "Drama" and known for its complex structure and experimental sound.
-
E.
Shutter
Shutter is a 2008 American supernatural horror film about a couple haunted by mysterious images in photographs, starring Joshua Jackson.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b904530081908bf341d842464856 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4b523f588819097389e067dda7f23 |
completed | April 19, 2026, 10:57 a.m. |
Created at: April 10, 2026, 10:24 a.m.