Triple
T30068817
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Agnes Maclehose |
E764116
|
entity |
| Predicate | hasLiteraryAlias |
P46855
|
FINISHED |
| Object | Clarinda |
—
|
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: Clarinda | Statement: [Agnes Maclehose, hasLiteraryAlias, Clarinda]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLiteraryAlias Context triple: [Agnes Maclehose, hasLiteraryAlias, Clarinda]
-
A.
hasFictionalAlias
Indicates that an entity is known by an alternative name or identity within a fictional context.
-
B.
hasAuthorAlias
chosen
Indicates that an entity (such as a person or author record) is known by an alternative name or pseudonym used as an author.
-
C.
hasHeteronymAuthor
Indicates that an entity has an author whose name is a heteronym (a word with the same spelling as another but different pronunciation and meaning).
-
D.
pseudonymCoinedBy
Indicates that a particular pseudonym was created or invented by a specific agent or source.
-
E.
alsoKnownAsRealAuthor
Indicates that an entity is an alternative or alias name identifying the same individual who is the actual (real) author of a work.
- 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_69f2247221388190a13a22c47094a0ef |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69fd19f791f48190bbb6f6047f9ddc59 |
completed | May 7, 2026, 11:02 p.m. |
| PD | Predicate disambiguation | batch_69fd0df365948190bc9bfc7ffd46acd8 |
completed | May 7, 2026, 10:10 p.m. |
Created at: April 29, 2026, 7 p.m.