Triple
T10118328
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maria Cantwell |
E223218
|
entity |
| Predicate | previousPositionStartTime |
P66434
|
FINISHED |
| Object | 1993-01-03 |
—
|
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: 1993-01-03 | Statement: [Maria Cantwell, previousPositionStartTime, 1993-01-03]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousPositionStartTime Context triple: [Maria Cantwell, previousPositionStartTime, 1993-01-03]
-
A.
previousLocationTime
Indicates the specific time at which an entity was located at its immediately preceding location before its current one.
-
B.
positionStartTime
chosen
Indicates the time at which a position, role, or placement begins.
-
C.
positionOnPast
Indicates that one entity occupied a specific position or location relative to another entity at some point in the past.
-
D.
endTimePosition
Indicates the temporal position or point in time at which an event, state, or interval comes to an end.
-
E.
currentPosition
Indicates the present role, job, or status an entity currently holds within a given context.
- 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_69ca8422047c81909d66b717b8b18cf3 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cdd26460a4819093a3b239d97c3e3d |
completed | April 2, 2026, 2:20 a.m. |
| PD | Predicate disambiguation | batch_69cd4b9ed7e48190aa132ef8a69b49f9 |
completed | April 1, 2026, 4:45 p.m. |
Created at: March 30, 2026, 9:04 p.m.