Triple
T13453196
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duke of Leuchtenberg |
E311161
|
entity |
| Predicate | holdersOftenServedIn |
P48460
|
FINISHED |
| Object | Russian Imperial service |
—
|
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: Russian Imperial service | Statement: [Duke of Leuchtenberg, holdersOftenServedIn, Russian Imperial service]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: holdersOftenServedIn Context triple: [Duke of Leuchtenberg, holdersOftenServedIn, Russian Imperial service]
-
A.
officeHoldersServeAt
Indicates that certain office holders perform their duties or serve in a specific office, institution, or jurisdiction.
-
B.
officeHoldersServeIn
chosen
Indicates that certain office holders perform their official duties or occupy their roles within a specified office, institution, or jurisdiction.
-
C.
officeHoldersParticipateIn
Indicates that individuals holding an office take part in or are involved in a specified event, activity, or process.
-
D.
hasMemberWhoServedOn
Indicates that a group or organization includes at least one member who has served on a specified body, committee, or entity.
-
E.
officeHoldersAreUsually
Indicates that individuals holding a particular office or position are typically or generally characterized by a specified property or role.
- 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_69d806a938b8819097ec43a2229fc7f9 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dbaefae85481909e6a59797cbb25e7 |
completed | April 12, 2026, 2:40 p.m. |
| PD | Predicate disambiguation | batch_69d9a03ce03481908c61094f0cc0c158 |
completed | April 11, 2026, 1:13 a.m. |
Created at: April 9, 2026, 9:41 p.m.