Triple
T30968798
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elegies (Propertius) |
E789032
|
entity |
| Predicate | firstBookFocus |
P81905
|
FINISHED |
| Object | intense love affair with Cynthia |
—
|
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: intense love affair with Cynthia | Statement: [Elegies (Propertius), firstBookFocus, intense love affair with Cynthia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstBookFocus Context triple: [Elegies (Propertius), firstBookFocus, intense love affair with Cynthia]
-
A.
firstBookBy
Indicates that one entity is the first book authored by another entity.
-
B.
firstBookCount
Indicates the number of books associated with the first entity in a given relationship or comparison.
-
C.
firstEditionFocus
Indicates that the primary emphasis or subject of something is its first edition.
-
D.
Book1Focus
chosen
Indicates that the primary attention, emphasis, or thematic concentration is placed on the first book in a set or sequence.
-
E.
firstBookCompleted
Indicates that an entity has finished reading, writing, or otherwise completing their first book.
- 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_69f224c3a6b48190951add9b7b7f0271 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_6a0352b6c7dc81908f190060eb1e1857 |
completed | May 12, 2026, 4:17 p.m. |
| PD | Predicate disambiguation | batch_6a03507c37d4819091068b2ec5cacef9 |
completed | May 12, 2026, 4:08 p.m. |
Created at: April 29, 2026, 8:54 p.m.