Triple
T21444193
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Melvill |
E529025
|
entity |
| Predicate | historicalSpellingOf |
P4181
|
FINISHED |
| Object | Herman Melville’s surname |
—
|
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: Herman Melville’s surname | Statement: [Melvill, historicalSpellingOf, Herman Melville’s surname]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: historicalSpellingOf Context triple: [Melvill, historicalSpellingOf, Herman Melville’s surname]
-
A.
originalSpelling
Indicates that one entity provides the initial or historically first-used spelling form of another entity’s name or term.
-
B.
scripturalSpelling
Indicates that one form of a word or name is the spelling used in a particular scriptural or sacred text.
-
C.
historicalForm
chosen
Indicates that one entity is an earlier or historically attested form or variant of another entity.
-
D.
historicallySpoke
Indicates that an entity used a particular language as a spoken language during some period in the past.
-
E.
historicalDialect
Indicates that one dialect is a historically earlier or ancestral form of another dialect.
- 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_69e0c457579481909db68053ed99750c |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e8b70630ac8190b031e31ffa2c358e |
completed | April 22, 2026, 11:54 a.m. |
| PD | Predicate disambiguation | batch_69e631df1b38819088d3604854e697b4 |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:05 p.m.