Triple
T33631757
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thomas Andersson |
E861580
|
entity |
| Predicate | surnameDerivedFromGivenName |
P54694
|
FINISHED |
| Object | Anders |
—
|
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: Anders | Statement: [Thomas Andersson, surnameDerivedFromGivenName, Anders]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: surnameDerivedFromGivenName Context triple: [Thomas Andersson, surnameDerivedFromGivenName, Anders]
-
A.
familyNameDerivedFrom
chosen
Indicates that one entity’s family name originates from, or is etymologically derived from, another entity.
-
B.
surnameVariant
Indicates that one surname is an alternative spelling, form, or variation of another surname.
-
C.
patronymicOrigin
Indicates that one entity’s name is derived from the name of a father or paternal ancestor of another entity.
-
D.
surnameUsedIn
Indicates that a particular surname is used or borne within a specified context, such as by a person, family, or group.
-
E.
surnamePortmanteauOf
Indicates that one surname is formed as a portmanteau by blending parts of two or more other surnames.
- 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_69f34981c54c81909b33c3fa2208a52d |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6f85bfba48190aba95b40642a8ca7 |
completed | May 3, 2026, 7:25 a.m. |
| PD | Predicate disambiguation | batch_69f6f6632dfc8190af85e258c8519207 |
completed | May 3, 2026, 7:16 a.m. |
Created at: May 1, 2026, 1:41 a.m.