Triple
T3419562
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Telegram |
E72084
|
entity |
| Predicate | softwareVersionType |
P46743
|
FINISHED |
| Object | proprietary software |
—
|
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: proprietary software | Statement: [Telegram, softwareVersionType, proprietary software]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: softwareVersionType Context triple: [Telegram, softwareVersionType, proprietary software]
-
A.
versionOf
Indicates that one entity is a specific form, edition, or variant derived from or corresponding to another entity.
-
B.
softwareName
Indicates that one entity is the name or title of a software application associated with another entity.
-
C.
hasVersionType
chosen
Indicates that one entity is associated with a specific kind or category of version of another entity.
-
D.
softwareTypeMaintained
Indicates that an entity is responsible for maintaining or supporting a particular type of software.
-
E.
exportVersionOf
Indicates that one entity is a version of another specifically created or designated for export (e.g., for external distribution or use).
- 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_69ad85ad38e48190b7660c5118a35289 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb94d6808819080997df30119e71e |
completed | March 8, 2026, 6 p.m. |
| PD | Predicate disambiguation | batch_69adadfcbc38819080852c18240451c5 |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:15 p.m.