Triple
T22607778
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Automatic Baby |
E566606
|
entity |
| Predicate | performedForEventType |
P120695
|
FINISHED |
| Object | inaugural ball |
—
|
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: inaugural ball | Statement: [Automatic Baby, performedForEventType, inaugural ball]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: performedForEventType Context triple: [Automatic Baby, performedForEventType, inaugural ball]
-
A.
performedForEvent
chosen
Indicates that an action or service was carried out specifically in connection with, or on behalf of, a particular event.
-
B.
performedEvent
Indicates that an entity carried out, executed, or was responsible for a particular event.
-
C.
introducedForEventType
Indicates that something was first created, implemented, or made available specifically in connection with a particular type of event.
-
D.
accessibleForEventType
Indicates that something can be used, reached, or is available in the context of a specified type or category of event.
-
E.
performedWhen
Indicates the specific time or temporal condition under which an action or event was carried out.
- 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_69e245884860819081046ce07d5872c4 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f167e75658819089153eab7563540c |
completed | April 29, 2026, 2:07 a.m. |
| PD | Predicate disambiguation | batch_69ee627be4248190889a88764624e174 |
completed | April 26, 2026, 7:07 p.m. |
Created at: April 17, 2026, 2:55 p.m.