Triple
T3253560
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grand Marshal |
E68241
|
entity |
| Predicate | maySupervise |
P9418
|
FINISHED |
| Object | Deputy Grand Marshal |
—
|
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: Deputy Grand Marshal | Statement: [Grand Marshal, maySupervise, Deputy Grand Marshal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maySupervise Context triple: [Grand Marshal, maySupervise, Deputy Grand Marshal]
-
A.
canSupervise
chosen
Indicates that one entity has the authority or capability to oversee, direct, or manage the work or activities of another entity.
-
B.
mayRuleOver
Indicates that one entity has the potential or permission to exercise authority or governance over another entity.
-
C.
mayConduct
Indicates that one entity is permitted or authorized to carry out, perform, or execute a particular action, process, or operation on or with another entity.
-
D.
mayServe
Indicates that one entity is permitted or authorized to provide a service or function to another entity.
-
E.
mayHold
Indicates that one entity is permitted or allowed to possess, contain, or maintain another entity.
- 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_69ad858f74408190bcbd07f967cd7bd0 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adaf640fd8819083c3c0cc41db2ffc |
completed | March 8, 2026, 5:18 p.m. |
| PD | Predicate disambiguation | batch_69ada41ae74081909a0d1d696be8e35e |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:09 p.m.