Triple
T10503103
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sung Mass |
E247718
|
entity |
| Predicate | hasComponent |
P35
|
FINISHED |
| Object | Kyrie |
E271995
|
NE 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: Kyrie | Statement: [Sung Mass, hasComponent, Kyrie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kyrie Context triple: [Sung Mass, hasComponent, Kyrie]
-
A.
Kyrie
chosen
Kyrie is the opening choral movement of J.S. Bach’s Mass in B minor, characterized by its solemn plea for mercy and intricate polyphonic writing.
-
B.
Kyrie
"Kyrie" is a science fiction short story by Poul Anderson that explores themes of alien contact, faith, and sacrifice.
-
C.
Kyrie
Kyrie is the given name of Kyrie Irving, a prominent NBA point guard known for his exceptional ball-handling and scoring ability.
-
D.
Kyrie
The "Kyrie" is the second movement of Mozart’s Requiem, a choral fugue that sets the traditional plea for mercy in a dramatic and contrapuntal style.
-
E.
Padrenostro
Padrenostro is an Italian drama film centered on terrorism and father-son relationships in 1970s Italy, for which Pierfrancesco Favino received critical acclaim.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d381c4aa948190942e1d803143fb0e |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d5099d62408190a6c6884411c6e423 |
completed | April 7, 2026, 1:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d8dccec72481909bcfb6a9c5df7ba9 |
completed | April 10, 2026, 11:19 a.m. |
Created at: April 6, 2026, 12:25 p.m.