Triple
T28666962
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Inspector John Raymond Legrasse |
E725608
|
entity |
| Predicate | sectionTitleOfAppearance |
P165193
|
FINISHED |
| Object | The Tale of Inspector Legrasse |
—
|
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: The Tale of Inspector Legrasse | Statement: [Inspector John Raymond Legrasse, sectionTitleOfAppearance, The Tale of Inspector Legrasse]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sectionTitleOfAppearance Context triple: [Inspector John Raymond Legrasse, sectionTitleOfAppearance, The Tale of Inspector Legrasse]
-
A.
titleSheetSections
Indicates that one or more sections are associated with, or belong to, a particular title sheet.
-
B.
titleAffirms
Indicates that a title explicitly asserts, confirms, or supports the truth or validity of a particular claim, idea, or relationship.
-
C.
titleOfPart
Indicates that one entity is the title specifically assigned to a part or section of another, larger work or resource.
-
D.
courtTitle
Indicates the official judicial position or title held by a person within a court system.
-
E.
sectionType
Indicates the specific kind or category of section that an entity belongs to or represents.
- F. None of above. chosen
Provenance (4 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_69f01d85be388190b669a0e401e2f2c4 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f65705a3048190a3728b695ba2ae65 |
completed | May 2, 2026, 7:56 p.m. |
| PD | Predicate disambiguation | batch_69f651ac855481908e30c3b345d31356 |
completed | May 2, 2026, 7:34 p.m. |
| PDg | Predicate description generation | batch_69f6562ef4e4819082ce6abd41b74dc5 |
completed | May 2, 2026, 7:53 p.m. |
Created at: April 28, 2026, 5:01 a.m.