Triple
T21986220
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lestrange family |
E542966
|
entity |
| Predicate | statusInWizardingWorld |
P64108
|
FINISHED |
| Object | ancient family |
—
|
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: ancient family | Statement: [Lestrange family, statusInWizardingWorld, ancient family]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: statusInWizardingWorld Context triple: [Lestrange family, statusInWizardingWorld, ancient family]
-
A.
magicalStatus
Indicates that an entity possesses, is affected by, or is characterized in terms of a particular magical condition or property.
-
B.
wardAtStMungos
Indicates that an entity is located in or assigned to a specific ward at St Mungo’s Hospital.
-
C.
roleInHarryPotter
Indicates that one entity has a specific role or character part within the Harry Potter series in relation to the other entity.
-
D.
hasProfessionInMuggleWorld
Indicates that an entity holds or practices a specific profession within the non-magical (Muggle) world.
-
E.
ministryOfMagicClassification
chosen
Indicates the official category or status assigned to something by the Ministry of Magic according to its classification system.
- 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_69e0c48136b081908831fa907cc02e18 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f12709cb288190a2620e337fea364c |
completed | April 28, 2026, 9:30 p.m. |
| PD | Predicate disambiguation | batch_69e6f6154e408190acc5b2c278acaff4 |
completed | April 21, 2026, 3:59 a.m. |
Created at: April 16, 2026, 8:04 p.m.