Triple
T5183196
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Petunia Dursley |
E116967
|
entity |
| Predicate | legalGuardianRole |
P18066
|
FINISHED |
| Object | Primary female guardian of Harry Potter |
—
|
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: Primary female guardian of Harry Potter | Statement: [Petunia Dursley, legalGuardianRole, Primary female guardian of Harry Potter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: legalGuardianRole Context triple: [Petunia Dursley, legalGuardianRole, Primary female guardian of Harry Potter]
-
A.
adoptionRole
Indicates the specific role an entity plays within an adoption relationship, such as adopter, adoptee, or intermediary.
-
B.
parentalRoleTo
chosen
Indicates a parental relationship in which one entity holds a parent role with respect to another entity.
-
C.
legalCaseRole
Indicates the specific role or capacity an entity holds within a legal case, such as plaintiff, defendant, judge, or attorney.
-
D.
legalSystemRole
Indicates the specific function, capacity, or position an entity holds within a legal or judicial system.
-
E.
adoptiveParent
Indicates that one entity is the legally recognized parent of another through adoption rather than biological descent.
- 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_69bd446140f08190becb93c61158f27f |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd799d50388190bf2b7dfdd90949e9 |
completed | March 20, 2026, 4:45 p.m. |
| PD | Predicate disambiguation | batch_69bd77b7e8b4819092ec3965e11f2dea |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:46 p.m.