Triple
T773106
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | As We Were Saying |
E16325
|
entity |
| Predicate | hasWikidataProperty |
P19013
|
FINISHED |
| Object | work by Charles Dudley Warner |
—
|
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: work by Charles Dudley Warner | Statement: [As We Were Saying, hasWikidataProperty, work by Charles Dudley Warner]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWikidataProperty Context triple: [As We Were Saying, hasWikidataProperty, work by Charles Dudley Warner]
-
A.
identifiesPropertyOf
Indicates that one entity specifies or denotes a particular property or attribute belonging to another entity.
-
B.
recognizedFormOfProperty
Indicates that one entity is acknowledged or accepted as a valid or official form, variant, or representation of a particular property associated with another entity.
-
C.
hasLanguageCodeOnWikipedia
Indicates that a particular language is represented on Wikipedia by a specific language code.
-
D.
isAssociatedWith
Indicates that there exists a connection, relationship, or involvement between two entities without specifying its exact nature.
-
E.
hasWKN
Indicates that an entity is associated with a specific Wertpapierkennnummer (WKN), i.e., a unique German securities identification code.
- 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_69a49369a0848190af883934cee3db4c |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a72eda6c81908205ae5a1e05cc20 |
completed | March 1, 2026, 8:53 p.m. |
| PD | Predicate disambiguation | batch_69a4a508c42c8190850a0ac7844a3ea9 |
completed | March 1, 2026, 8:43 p.m. |
| PDg | Predicate description generation | batch_69a4a5a35c68819082429755c046e9a7 |
completed | March 1, 2026, 8:46 p.m. |
Created at: March 1, 2026, 7:37 p.m.