Triple
T3786886
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beyond: Two Souls |
E85549
|
entity |
| Predicate | windowsReleaseYear |
P51505
|
FINISHED |
| Object | 2019 |
—
|
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: 2019 | Statement: [Beyond: Two Souls, windowsReleaseYear, 2019]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: windowsReleaseYear Context triple: [Beyond: Two Souls, windowsReleaseYear, 2019]
-
A.
windowsReleaseDate
Indicates the calendar date on which a specific version of Microsoft Windows was officially released.
-
B.
windows
Indicates that one entity is a window of, or is associated as a window-related component or feature to, another entity.
-
C.
deploymentYear
Indicates the calendar year in which an entity (such as a system, product, or resource) was first put into active use or operation.
-
D.
EPReleaseYear
Indicates the calendar year in which an EP (extended play recording) was officially released.
-
E.
ARVersionAnnouncementYear
Indicates the year in which a specific version of an augmented reality (AR) product or system was officially announced.
- F. None of above. chosen
Provenance (4 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_69aed937fa8881908208ef3801060826 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aee634c6ac819099653c660c286746 |
completed | March 9, 2026, 3:24 p.m. |
| PD | Predicate disambiguation | batch_69aee3d3c92c819081d9d5c45ef37a5d |
completed | March 9, 2026, 3:14 p.m. |
| PDg | Predicate description generation | batch_69aee633dab88190b14cec8afb19ca6a |
completed | March 9, 2026, 3:24 p.m. |
Created at: March 9, 2026, 3:13 p.m.