Triple
T9497703
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Quartz (Apple graphics) |
E229050
|
entity |
| Predicate | fileFormatSupport |
P8463
|
FINISHED |
| Object |
E29775
|
NE 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: PDF | Statement: [Quartz (Apple graphics), fileFormatSupport, PDF]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: PDF Context triple: [Quartz (Apple graphics), fileFormatSupport, PDF]
-
A.
PDF/E
PDF/E is an ISO-standardized subset of the PDF format designed specifically for reliable creation, exchange, and archiving of engineering and technical documents, such as CAD and geospatial data.
-
B.
PDF/A
PDF/A is an ISO-standardized version of the PDF format designed specifically for long-term archiving and reliable reproduction of electronic documents.
-
C.
Pades
Pades is a village in northwestern Greece located in the mountainous region near Mount Smolikas.
-
D.
Portable Document Format
chosen
Portable Document Format (PDF) is a widely used file format designed for reliably presenting and exchanging documents independent of software, hardware, or operating systems.
-
E.
PDF/VT
PDF/VT is an ISO-standardized subset of the PDF format designed specifically for variable and transactional printing, enabling efficient, high-volume personalized document production.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca84753660819098e8d416e89e26ae |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd95ef06b88190b7a840caddea3e38 |
completed | April 1, 2026, 10:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d12d3aafb88190ac53289039bca88a |
completed | April 4, 2026, 3:24 p.m. |
Created at: March 30, 2026, 7:56 p.m.