Triple
T37990653
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Universal Media Disc |
E947814
|
entity |
| Predicate | readingDevice |
P69310
|
FINISHED |
| Object | UMD drive in PlayStation Portable |
—
|
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: UMD drive in PlayStation Portable | Statement: [Universal Media Disc, readingDevice, UMD drive in PlayStation Portable]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: readingDevice Context triple: [Universal Media Disc, readingDevice, UMD drive in PlayStation Portable]
-
A.
readingTechnology
Indicates a relationship where a reading activity involves or is carried out using a particular technology.
-
B.
readingSystem
chosen
Indicates a system or device that presents, interprets, or processes written or digital content for a user.
-
C.
readingOrganizer
Indicates that an entity is responsible for planning, managing, or coordinating reading-related activities or materials for others.
-
D.
readingOf
Indicates that one entity is an interpretation, measurement, or recorded value derived from another entity.
-
E.
readingType
Indicates the specific kind or category of reading associated with a measurement, observation, or recorded value.
- 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_69f76ef8a1d08190a741bbbc5970e3b3 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbc995dc2481908b3bd4217f8101e7 |
completed | May 6, 2026, 11:07 p.m. |
| PD | Predicate disambiguation | batch_69fbc8ee04f08190977b7ad70fc85896 |
completed | May 6, 2026, 11:04 p.m. |
Created at: May 3, 2026, 4:20 p.m.