Triple
T19825592
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gonzalo |
E476316
|
entity |
| Predicate | saves |
P18723
|
FINISHED |
| Object | Prospero |
—
|
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: Prospero | Statement: [Gonzalo, saves, Prospero]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Prospero Context triple: [Gonzalo, saves, Prospero]
-
A.
Prospero
Prospero was the birth name of Pope Benedict XIV, an 18th-century pope noted for his scholarship and efforts to reconcile church doctrine with Enlightenment thought.
-
B.
Prospero
chosen
Prospero is the powerful sorcerer and rightful Duke of Milan who orchestrates the events on a remote island in Shakespeare’s play "The Tempest."
-
C.
Prospero
Prospero is the internal codename that was reportedly used by Sony during the development of the PlayStation 5 console.
-
D.
Prospero
Prospero is an Italian surname notably borne by figures such as Ada Prospero Gobetti, a prominent anti-fascist, writer, and intellectual.
-
E.
Próspero
Próspero is the given name of Próspero Fernández Oreamuno, a 19th-century Costa Rican president and political figure.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e51c7c188190b926f3a2a7b5f881 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e656c9e7348190a569a40bd1fca6ba |
completed | April 20, 2026, 4:39 p.m. |
Created at: April 10, 2026, 1:50 p.m.