Triple
T35385714
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Methuen Home for Girls |
E1022786
|
entity |
| Predicate | hasStaffRoleInFiction |
P61558
|
FINISHED |
| Object | janitor |
—
|
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: janitor | Statement: [Methuen Home for Girls, hasStaffRoleInFiction, janitor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasStaffRoleInFiction Context triple: [Methuen Home for Girls, hasStaffRoleInFiction, janitor]
-
A.
hasRankInFiction
Indicates that a fictional character or entity holds a specific rank, title, or hierarchical position within a fictional context or universe.
-
B.
hasFictionalStaffMember
chosen
Indicates that an entity includes or employs a staff member who is a fictional character.
-
C.
hasStaffTypeInStory
Indicates that a story involves or is associated with a particular type or category of staff.
-
D.
hasFictionalAuthor
Indicates that one entity is the fictional or in-universe author of a work attributed to them.
-
E.
hasSkillInFiction
Indicates that an entity possesses skill or proficiency in the domain of fiction.
- 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_69f76df28d8c819089f2c5799fe7d079 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69ffecdcbac4819093b725a7dbe0e61b |
completed | May 10, 2026, 2:26 a.m. |
| PD | Predicate disambiguation | batch_69ffec3633288190adbbd84e277708dc |
completed | May 10, 2026, 2:23 a.m. |
Created at: May 3, 2026, 4:03 p.m.