Triple
T25209389
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Scarlett Amber Perkins |
E631639
|
entity |
| Predicate | laterReturnsTo |
P45021
|
FINISHED |
| Object | the town with the graveyard |
—
|
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: the town with the graveyard | Statement: [Scarlett Amber Perkins, laterReturnsTo, the town with the graveyard]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterReturnsTo Context triple: [Scarlett Amber Perkins, laterReturnsTo, the town with the graveyard]
-
A.
returnsTo
chosen
Indicates that an entity goes back to a previous location, state, or entity it was associated with before.
-
B.
forcedToReturnTo
Indicates that one entity is compelled, against its preference or by external pressure or requirement, to go back to a previous place, state, or situation.
-
C.
returnedDuring
Indicates that one entity was given back or restored to another entity within a specified time period or event.
-
D.
returnedFrom
Indicates that an entity has come back or been sent back from a specified source, location, or prior state.
-
E.
returnedFor
Indicates that an entity has been sent, given, or brought back in response to, or on behalf of, another entity or prior action.
- 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_69e75a8d1aa48190a4320acd3654762c |
completed | April 21, 2026, 11:07 a.m. |
| NER | Named-entity recognition | batch_69f6640168948190811bd5f933a87cf5 |
completed | May 2, 2026, 8:52 p.m. |
| PD | Predicate disambiguation | batch_69f6633451948190bcc0410602bb4914 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 21, 2026, 12:58 p.m.