Triple
T9004572
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Live Photos |
E215111
|
entity |
| Predicate | hasEditingFeature |
P85679
|
FINISHED |
| Object | change key photo |
—
|
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: change key photo | Statement: [Live Photos, hasEditingFeature, change key photo]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEditingFeature Context triple: [Live Photos, hasEditingFeature, change key photo]
-
A.
hasEditingModel
Indicates that one entity is associated with another entity that serves as its editing or modification model.
-
B.
hasEditionFeature
Indicates that one edition of a work includes a specific feature, characteristic, or component that distinguishes it from other editions.
-
C.
hasEditorType
Indicates that an entity has an associated kind or category of editor responsible for reviewing or modifying it.
-
D.
hasEditorScripting
Indicates that an entity provides or supports scripting capabilities specifically for editing or editor-related functionality.
-
E.
hasEditingStyle
Indicates that one entity possesses or is characterized by a particular manner or approach to editing.
- 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_69ca83a12d648190b1e4fe11e8a31890 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6959497c8190a748c78504dd2eb6 |
completed | April 1, 2026, 12:39 a.m. |
| PD | Predicate disambiguation | batch_69cc5edf84408190aa5f57cb8bfd00e1 |
completed | March 31, 2026, 11:55 p.m. |
| PDg | Predicate description generation | batch_69cc5f6dec4081909379bd57c02a5710 |
completed | March 31, 2026, 11:57 p.m. |
Created at: March 30, 2026, 7:05 p.m.