Triple
T36407081
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Robert Walton's ship |
E896774
|
entity |
| Predicate | hasCommunicationForm |
P112150
|
FINISHED |
| Object | epistolary letters |
—
|
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: epistolary letters | Statement: [Robert Walton's ship, hasCommunicationForm, epistolary letters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCommunicationForm Context triple: [Robert Walton's ship, hasCommunicationForm, epistolary letters]
-
A.
hasCommunicationType
chosen
Indicates that one entity uses, supports, or is associated with a particular form or mode of communication.
-
B.
hasCommunicationAccess
Indicates that one entity is able to communicate with, or use a communication channel or service provided by, another entity.
-
C.
hasOnlineForm
Indicates that an entity provides or is associated with a form that can be accessed and completed online.
-
D.
hasCommunicationUse
Indicates that something is used for, or serves the purpose of, communication.
-
E.
hasCorrespondenceForm
Indicates that there exists a specific format, template, or structural representation used for the correspondence associated with an 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_69f76e53b81081908d3b81860593f38a |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a037c8d06cc8190ab6a5e18d9d2571e |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a0a54cc8190868c1bfa1590d1a6 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:10 p.m.