Triple
T17603417
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pope Celestine III |
E428763
|
entity |
| Predicate | birthName |
P65
|
FINISHED |
| Object | Hyacinth Bobone |
—
|
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: Hyacinth Bobone | Statement: [Pope Celestine III, birthName, Hyacinth Bobone]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hyacinth Bobone Context triple: [Pope Celestine III, birthName, Hyacinth Bobone]
-
A.
Hyacinth Bobone
chosen
Hyacinth Bobone is the birth name of Pope Celestine III, a 12th-century head of the Catholic Church known for his role in medieval European politics.
-
B.
Aroldo
Aroldo is a lesser-known opera by Italian composer Giuseppe Verdi, adapted from his earlier work Stiffelio and set in medieval England and Scotland.
-
C.
Wilder Guisao
Wilder Guisao is a Colombian professional footballer known for playing as a winger for clubs in South America and abroad.
-
D.
Doumer
Doumer is a French surname most notably borne by Paul Doumer, the 13th President of France.
-
E.
Zito
Zito is a surname most notably associated with Barry Zito, a former Major League Baseball pitcher and Cy Young Award winner.
- 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_69d889e1c6148190ba76241e74688f8b |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e46c4a9a948190bc857f5da9dc7444 |
completed | April 19, 2026, 5:46 a.m. |
Created at: April 10, 2026, 5:51 a.m.