Triple
T29842313
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gilda |
E757832
|
entity |
| Predicate | sacrificesHerselfToSave |
P113058
|
FINISHED |
| Object | Duke of Mantua |
—
|
NE NERFINISHED |
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: Duke of Mantua | Statement: [Gilda, sacrificesHerselfToSave, Duke of Mantua]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sacrificesHerselfToSave Context triple: [Gilda, sacrificesHerselfToSave, Duke of Mantua]
-
A.
sacrificedLifeToSaveOthers
chosen
Indicates that an entity willingly gave up their own life in order to protect or rescue other entities.
-
B.
sacrifice
Indicates giving up something of value, often for the benefit, protection, or advantage of another entity or goal.
-
C.
resultOfSacrifice
Indicates that something exists or occurs as the outcome or consequence of a sacrificial act.
-
D.
sacrificeType
Indicates the specific kind or category of sacrifice involved in a sacrificial action or relationship.
-
E.
sacrificedTo
Indicates that one entity is offered or given up as a sacrifice in honor of, or to appease, another entity.
- 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_69f224593f6c81908785a560fe659f58 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f6760b3d6081909d0e3748483989a4 |
completed | May 2, 2026, 10:09 p.m. |
| PD | Predicate disambiguation | batch_69f66ac32b60819092290b2de35988d3 |
completed | May 2, 2026, 9:21 p.m. |
Created at: April 29, 2026, 5:40 p.m.