Triple
T31958474
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Ryan |
E815970
|
entity |
| Predicate | eventStartLocation |
P91966
|
FINISHED |
| Object | Savernake Forest, Wiltshire, England |
—
|
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: Savernake Forest, Wiltshire, England | Statement: [Michael Ryan, eventStartLocation, Savernake Forest, Wiltshire, England]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eventStartLocation Context triple: [Michael Ryan, eventStartLocation, Savernake Forest, Wiltshire, England]
-
A.
eventLocationDetail
Indicates the specific place or venue where an event occurs, often providing more granular location information than a general address or area.
-
B.
locationOfEventOrganized
Indicates the place where a particular organized event is held or takes place.
-
C.
locationOfEventDescribed
Indicates that one entity is the place or setting where the event described by another entity occurs.
-
D.
eventLocationOfNotableActivity
Indicates that a location is the place where a notable or significant activity or event involving the related entity occurred.
-
E.
activityStartPlace
chosen
Indicates the location where an activity begins or is initiated.
- 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_69f348f4ec708190abbb2a7c3ed58844 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f71f8ee0688190bd025f27993452d3 |
completed | May 3, 2026, 10:12 a.m. |
| PD | Predicate disambiguation | batch_69f71cc405c08190863565609a4c8499 |
completed | May 3, 2026, 10 a.m. |
Created at: May 1, 2026, 12:08 a.m.