Triple
T23170424
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Some Lessons Learned (Kristin Chenoweth album cover) |
E578841
|
entity |
| Predicate | languageOfTextOnImage |
P128895
|
FINISHED |
| Object | English |
—
|
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: English | Statement: [Some Lessons Learned (Kristin Chenoweth album cover), languageOfTextOnImage, English]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageOfTextOnImage Context triple: [Some Lessons Learned (Kristin Chenoweth album cover), languageOfTextOnImage, English]
-
A.
languageOfTextInImages
chosen
Indicates the language used in the textual content that appears within images.
-
B.
languageText
Indicates that a piece of text is expressed in, or associated with, a particular language.
-
C.
filmPosterCaptionLanguage
Indicates the language in which the caption or text on a film’s poster is written.
-
D.
contentLanguage
Indicates the language in which the content is expressed or intended to be understood.
-
E.
languageOfLetters
Indicates that one entity is the language in which the other entity’s letters or written correspondence are composed.
- 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_69e245fd2a388190b814c0dfa15f7148 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18f2f10208190b3a0f9a4c790cb0a |
completed | April 29, 2026, 4:55 a.m. |
| PD | Predicate disambiguation | batch_69ef89ff76808190808ee4ad9dea776b |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 4:03 p.m.