Triple
T37701990
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Song of Flirting |
E939088
|
entity |
| Predicate | hasLanguageOfOriginalTitle |
P3048
|
FINISHED |
| Object | Portuguese |
—
|
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: Portuguese | Statement: [Song of Flirting, hasLanguageOfOriginalTitle, Portuguese]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLanguageOfOriginalTitle Context triple: [Song of Flirting, hasLanguageOfOriginalTitle, Portuguese]
-
A.
originalTitleLanguage
chosen
Indicates the language in which a work’s original title was written or expressed.
-
B.
originalLanguageTitle
Indicates the title of a work as it appears in its original language of creation or publication.
-
C.
hasOriginalWorkEnglishTitle
Indicates that an entity has an associated original work whose title is given in English.
-
D.
appearsInOriginalLanguage
Indicates that something (such as a work, text, or content) is presented or occurs in the language in which it was originally created, rather than in translation.
-
E.
languageOfAlternativeTitle
Indicates the language in which an alternative or variant title of an entity is expressed.
- 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_69f76eda6ae48190b3111071eeacc038 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fff09dae088190bd8460060d778feb |
completed | May 10, 2026, 2:42 a.m. |
| PD | Predicate disambiguation | batch_69fff0027c5c8190baa5c7a15852cbe0 |
completed | May 10, 2026, 2:40 a.m. |
Created at: May 3, 2026, 4:18 p.m.