Triple
T33068128
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maxims of State |
E846157
|
entity |
| Predicate | authorTitleOfAuthor |
P75519
|
FINISHED |
| Object | 1st Marquess of Halifax |
—
|
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: 1st Marquess of Halifax | Statement: [Maxims of State, authorTitleOfAuthor, 1st Marquess of Halifax]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: authorTitleOfAuthor Context triple: [Maxims of State, authorTitleOfAuthor, 1st Marquess of Halifax]
-
A.
authorTitle
Indicates that a person is the creator or writer of a work that bears the specified title.
-
B.
hasAuthorTitle
chosen
Indicates that an author holds or is designated by a specific title (e.g., professional, honorific, or role-based).
-
C.
authorName
Indicates the name associated with the person or entity that authored a given work or resource.
-
D.
originalTitleAuthorName
Indicates that the associated name is the author of the work’s original title.
-
E.
authorAsCredited
Indicates the relationship between a work and the person or entity credited as its author, regardless of actual authorship.
- 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_69f3495405b88190967af2157b43b896 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fd509e6bc08190b263923c2f40fea3 |
completed | May 8, 2026, 2:55 a.m. |
| PD | Predicate disambiguation | batch_69fd4fd1a58881909d4b84de1b24e380 |
completed | May 8, 2026, 2:52 a.m. |
Created at: May 1, 2026, 1:25 a.m.