Triple
T4117835
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Morris |
E90336
|
entity |
| Predicate | usedObjectInEscape |
P22475
|
FINISHED |
| Object | improvised raft made from raincoats |
—
|
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: improvised raft made from raincoats | Statement: [Frank Morris, usedObjectInEscape, improvised raft made from raincoats]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedObjectInEscape Context triple: [Frank Morris, usedObjectInEscape, improvised raft made from raincoats]
-
A.
usedResource
chosen
Indicates that an entity has utilized or consumed a particular resource in performing an action or achieving a result.
-
B.
usedInDetector
Indicates that something (e.g., a component, material, or method) is employed as part of a detector or detection system.
-
C.
usedMark
Indicates that one entity has employed or applied a particular mark, symbol, or indicator in some context or action.
-
D.
usedInExpression
Indicates that one entity (typically a term, symbol, or construct) is employed as a component within another entity that represents an expression.
-
E.
usedUntil
Indicates that something remained in use or operation up to a specified time or event, after which it was no longer used.
- 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_69aed95c080881908125e30c5dcdc6f8 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af0246e40081908ad6741a830ca68e |
completed | March 9, 2026, 5:24 p.m. |
| PD | Predicate disambiguation | batch_69af01867698819098e4144634b2ec4f |
completed | March 9, 2026, 5:21 p.m. |
Created at: March 9, 2026, 3:41 p.m.