Triple
T37464498
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Twinspell |
E930999
|
entity |
| Predicate | worksInBothFormats |
P26987
|
FINISHED |
| Object | Standard at time of release |
—
|
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: Standard at time of release | Statement: [Twinspell, worksInBothFormats, Standard at time of release]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: worksInBothFormats Context triple: [Twinspell, worksInBothFormats, Standard at time of release]
-
A.
operatesInFormat
Indicates that an entity functions, performs its role, or is carried out using a specified format.
-
B.
presentedInFormat
Indicates that something is expressed, delivered, or made available using a particular format or representation.
-
C.
relatedFormat
chosen
Indicates that two resources are available in different but closely related formats or media representations of essentially the same content.
-
D.
basedInWorkFormat
Indicates that an entity operates or is situated within a particular work format (such as remote, hybrid, or on-site) as its primary mode of working.
-
E.
fileFormatStandard
Indicates that something conforms to, specifies, or defines a standardized structure and rules for how data is organized and stored in a file.
- 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_69f76ec1a1148190b0a961f188d621b0 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fd02680d948190a3463fb119ba8556 |
completed | May 7, 2026, 9:21 p.m. |
| PD | Predicate disambiguation | batch_69fcf89c69b4819082bbc564bd15137d |
completed | May 7, 2026, 8:39 p.m. |
Created at: May 3, 2026, 4:17 p.m.