Triple
T274606
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eureka Conference |
E5217
|
entity |
| Predicate | attendeeRole |
P4073
|
FINISHED |
| Object | Roosevelt as President of the United States |
—
|
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: Roosevelt as President of the United States | Statement: [Eureka Conference, attendeeRole, Roosevelt as President of the United States]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: attendeeRole Context triple: [Eureka Conference, attendeeRole, Roosevelt as President of the United States]
-
A.
participantType
Indicates the specific role or category that a participant has within a given event, activity, or relationship.
-
B.
eventRole
chosen
Indicates the specific function, capacity, or part an entity plays within an event or occurrence.
-
C.
typeOfRole
Indicates that one entity specifies the kind or category of role that another entity holds or performs.
-
D.
identificationRole
Indicates that an entity serves as an identifier or plays a role in uniquely distinguishing or recognizing another entity.
-
E.
allianceRole
Indicates the specific function, status, or responsibility an entity holds within an alliance or cooperative partnership.
- 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_69a257e6c8788190987dfe705ca2912a |
completed | Feb. 28, 2026, 2:50 a.m. |
| NER | Named-entity recognition | batch_69a25dd1cdf881909c2c9b77b7f88684 |
completed | Feb. 28, 2026, 3:15 a.m. |
| PD | Predicate disambiguation | batch_69a25b7345c4819086c21710864a1b42 |
completed | Feb. 28, 2026, 3:05 a.m. |
Created at: Feb. 28, 2026, 2:59 a.m.