Triple
T31372200
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Schauspiel Frankfurt |
E800192
|
entity |
| Predicate | previousIntendant |
P12937
|
FINISHED |
| Object | Oliver Reese |
—
|
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: Oliver Reese | Statement: [Schauspiel Frankfurt, previousIntendant, Oliver Reese]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousIntendant Context triple: [Schauspiel Frankfurt, previousIntendant, Oliver Reese]
-
A.
previousAdministrator
chosen
Indicates that one entity formerly held an administrative role or position over another entity before the current administrator.
-
B.
predecessorAsFrenchCoSovereign
Indicates that one entity served immediately before another as a French co-sovereign in a shared rulership position.
-
C.
predecessorAsDukeOfNemours
Indicates that one entity previously held the title of Duke of Nemours immediately before another entity.
-
D.
predecessorInRegency
Indicates that one regent directly preceded another in holding regency authority over the same domain or office.
-
E.
previousMonarch
Indicates that one entity served as the monarch immediately before another entity in a succession.
- 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_69f224e6b7448190ac6bf97ad7364160 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fe6739d4dc8190ae7505c089bbac29 |
completed | May 8, 2026, 10:44 p.m. |
| PD | Predicate disambiguation | batch_69fe6541dffc81909c66a61ba69f38fc |
completed | May 8, 2026, 10:35 p.m. |
Created at: April 29, 2026, 9:18 p.m.