Triple
T27106681
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ralph Northam |
E686596
|
entity |
| Predicate | servedInVirginiaSenateUntil |
P14818
|
FINISHED |
| Object | 2014 |
—
|
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: 2014 | Statement: [Ralph Northam, servedInVirginiaSenateUntil, 2014]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servedInVirginiaSenateUntil Context triple: [Ralph Northam, servedInVirginiaSenateUntil, 2014]
-
A.
servedAsLieutenantGovernorOfVirginiaUntil
Indicates that a person held the position of Lieutenant Governor of Virginia up to a specified end date or point in time.
-
B.
servedAsLieutenantGovernorOfVirginiaFrom
Indicates that a person held the office of Lieutenant Governor of Virginia starting from a specified date or time period.
-
C.
succeededInOfficeAsSenatorBy
Indicates that one senator left office and was directly followed in that same senatorial position by another specific senator.
-
D.
senateMembership
chosen
Indicates that an entity holds or has held a position as a member of a senate.
-
E.
hasSenateSeatsSince
Indicates that an entity has held a specified number of seats in a senate starting from a particular point in time.
- 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_69ef148accd48190b6ed6e13a15f2a4f |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69fb563aec448190875410fb1a3ed624 |
completed | May 6, 2026, 2:54 p.m. |
| PD | Predicate disambiguation | batch_69fb35b9ede881908aaae93a215525df |
completed | May 6, 2026, 12:36 p.m. |
Created at: April 27, 2026, 8:51 a.m.