Triple
T37317006
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marcus Fulvius Nobilior |
E926363
|
entity |
| Predicate | hasCognomenMeaning |
P97319
|
FINISHED |
| Object | “more noble” in Latin |
—
|
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: “more noble” in Latin | Statement: [Marcus Fulvius Nobilior, hasCognomenMeaning, “more noble” in Latin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCognomenMeaning Context triple: [Marcus Fulvius Nobilior, hasCognomenMeaning, “more noble” in Latin]
-
A.
etymologyOfCognomen
chosen
Indicates that one term specifies the linguistic origin or derivation of a particular cognomen (surname or family name).
-
B.
memberHasCognomen
Indicates that a member is associated with or bears a specific cognomen (surname or additional family name).
-
C.
cognomenOf
Indicates that one entity is the cognomen (surname or family name) of another entity.
-
D.
hasAncestralFamilyNameMeaning
Indicates that an entity’s ancestral family name carries a specific meaning or significance.
-
E.
hasLatinNameMeaning
Indicates that an entity’s Latin name conveys a specific meaning or refers to a particular concept.
- 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_69f76eb28af88190b093b32e3fd614ab |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c8efcd4819088c2aeead65d93df |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a11efc08190bb7cacc1325b4dc6 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:16 p.m.