Triple
T32152369
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Crawford |
E821192
|
entity |
| Predicate | stateOfOriginOfCase |
P194908
|
FINISHED |
| Object | Washington |
—
|
NE NERFINISHED |
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: Washington | Statement: [Michael Crawford, stateOfOriginOfCase, Washington]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stateOfOriginOfCase Context triple: [Michael Crawford, stateOfOriginOfCase, Washington]
-
A.
stateOfOriginDebut
Indicates the event or match in which an individual first appeared in a State of Origin representative context.
-
B.
stateOfOriginRole
Indicates that a role or position is associated with, or originates from, a particular state or region.
-
C.
stateOfNigeria
Indicates that the subject is the sovereign nation-state known as Nigeria or pertains to it as a political entity.
-
D.
stateOfOriginDebutFor
Indicates that an entity made its first appearance or debut in a State of Origin event, team, or series for a specified side or jurisdiction.
-
E.
stateOfOriginAppearances
Indicates the number of times an entity has appeared in state-of-origin level events or competitions.
- F. None of above. chosen
Provenance (4 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_69f3490520d081909b2f1271dab75faa |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fd8e5f7c4c8190ab8e2f2a7bb1bd79 |
completed | May 8, 2026, 7:18 a.m. |
| PD | Predicate disambiguation | batch_69fd8d8a16f08190b9e880901bfa44fe |
completed | May 8, 2026, 7:15 a.m. |
| PDg | Predicate description generation | batch_69fd8e5e9ca48190890a2caddc1f9f5c |
completed | May 8, 2026, 7:18 a.m. |
Created at: May 1, 2026, 12:31 a.m.