Triple
T33585035
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Louis Cropa |
E860255
|
entity |
| Predicate | hasSurnameInWork |
P195936
|
FINISHED |
| Object | "Cropa" |
—
|
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: "Cropa" | Statement: [Louis Cropa, hasSurnameInWork, "Cropa"]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSurnameInWork Context triple: [Louis Cropa, hasSurnameInWork, "Cropa"]
-
A.
hasLastNameInWork
chosen
Indicates that a person or character is referred to by a specific last name within a particular work (e.g., book, film, or other creative piece).
-
B.
hasFullNameInWork
Indicates that an entity is referred to by a specific full name within a particular work or publication.
-
C.
hasGivenNameInWork
Indicates that a work specifies or uses a particular given (first) name for an entity or character.
-
D.
isOccupationalSurname
Indicates that a surname originates from or is derived from a person’s occupation or trade.
-
E.
hasAuthorSurname
Indicates that an entity (such as a work or publication) has an associated author whose family name is the specified surname.
- 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_69f3497e70e48190951c94d072879bec |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69ff59b33a38819086cc9aa19b81748b |
completed | May 9, 2026, 3:58 p.m. |
| PD | Predicate disambiguation | batch_69ff587758f88190a39c2164341dc554 |
completed | May 9, 2026, 3:53 p.m. |
Created at: May 1, 2026, 1:40 a.m.