Triple
T8895760
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amores |
E211800
|
entity |
| Predicate | openingPoemFeatures |
P27129
|
FINISHED |
| Object | Cupid taking a metrical foot |
—
|
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: Cupid taking a metrical foot | Statement: [Amores, openingPoemFeatures, Cupid taking a metrical foot]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: openingPoemFeatures Context triple: [Amores, openingPoemFeatures, Cupid taking a metrical foot]
-
A.
readPoemAt
Indicates that an entity reads or performs a poem at a specific time, place, or event.
-
B.
openingVerseType
Indicates the specific kind or category of an opening verse used at the beginning of a text, performance, or composition.
-
C.
openingVerseTheme
chosen
Indicates the primary idea or motif expressed in the opening verse of a text, song, or poem.
-
D.
viewsPoetryAs
Indicates that one entity regards or interprets poetry in a particular way or from a specific perspective.
-
E.
openingMotif
Indicates that one element serves as the initial recurring theme or pattern that introduces and sets the tone for another element, such as a work or sequence.
- 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_69ca83918d3081909b326fa3750cb8c8 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc61bfec0881908e4ef5b7f0e6b542 |
completed | April 1, 2026, 12:07 a.m. |
| PD | Predicate disambiguation | batch_69cc5c2aec04819093c932fe51c0f08d |
completed | March 31, 2026, 11:43 p.m. |
Created at: March 30, 2026, 6:54 p.m.