Triple
T12422452
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Savoy Theatre |
E296808
|
entity |
| Predicate | firstToUse |
P27625
|
FINISHED |
| Object | electric lighting throughout the auditorium |
—
|
LITERAL 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: electric lighting throughout the auditorium | Statement: [Savoy Theatre, firstToUse, electric lighting throughout the auditorium]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstToUse Context triple: [Savoy Theatre, firstToUse, electric lighting throughout the auditorium]
-
A.
firstUsedFor
Indicates that one entity was the earliest or original thing for which another entity was used or applied.
-
B.
firstUsedBy
chosen
Indicates that something was initially utilized, applied, or employed by a particular entity before any others.
-
C.
firstOf
Indicates that one entity is the earliest or initial member in an ordered sequence or collection relative to the others.
-
D.
firstUsedAt
Indicates the time or place at which something was initially used or put into operation.
-
E.
firstProminentlyUsedAfter
Indicates that one entity began to be widely or notably used only after the time or event associated with 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_69d6ada0640c81908c061d7fb3d47786 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94e1888b48190bd750f839a26e99e |
completed | April 10, 2026, 7:23 p.m. |
| PD | Predicate disambiguation | batch_69d94d354b488190adc83fb4f2770dd5 |
completed | April 10, 2026, 7:19 p.m. |
Created at: April 8, 2026, 9:55 p.m.