Triple
T36191285
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Upside Down Cake |
E1046995
|
entity |
| Predicate | introducedForVersion |
P11235
|
FINISHED |
| Object | Android 14 |
—
|
NE NERFINISHED |
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: Android 14 | Statement: [Upside Down Cake, introducedForVersion, Android 14]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: introducedForVersion Context triple: [Upside Down Cake, introducedForVersion, Android 14]
-
A.
introducedVersionOf
Indicates that one entity is the version in which another entity was first introduced or made available.
-
B.
introducedWithVersion
chosen
Indicates that something first became available or was added starting from a specific version.
-
C.
introducedFor
Indicates that one entity was presented or brought to the attention of another entity for a specific purpose or role.
-
D.
introducedFrom
Indicates that one entity was brought, originated, or caused to appear in a context, system, or environment by another entity.
-
E.
messageIntroducedWith
Indicates that one message is presented or initiated by means of another message or introductory content.
- 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_69f76e3d4fbc81908c159c7beeb4ce00 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fe91383a1c81909266e40c3c3ede6c |
completed | May 9, 2026, 1:43 a.m. |
| PD | Predicate disambiguation | batch_69fe8fde094081908f0f121664fbb5c7 |
completed | May 9, 2026, 1:37 a.m. |
Created at: May 3, 2026, 4:08 p.m.