Triple
T31059524
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hogwarts infirmary scenes |
E791491
|
entity |
| Predicate | hasPrimaryHealer |
P201915
|
FINISHED |
| Object | Madam Pomfrey |
—
|
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: Madam Pomfrey | Statement: [Hogwarts infirmary scenes, hasPrimaryHealer, Madam Pomfrey]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrimaryHealer Context triple: [Hogwarts infirmary scenes, hasPrimaryHealer, Madam Pomfrey]
-
A.
hasPrimaryCharacter
Indicates that an entity features another entity as its main or central character.
-
B.
hasPrimaryDefender
Indicates that one entity serves as the main or principal protector or defender of another entity.
-
C.
hasPrimaryAbility
Indicates that an entity possesses a main or most important ability that characterizes its primary function or role.
-
D.
hasSecondarySpirit
Indicates that an entity is associated with an additional, subordinate, or supporting spirit beyond its primary one.
-
E.
hasCure
Indicates that one entity serves as a remedy or treatment that can eliminate or effectively counteract a disease, condition, or problem affecting another entity.
- 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_69f224cb08908190ba71ad9aa87518ed |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_6a0031ed5d708190ab93516ad081ada6 |
completed | May 10, 2026, 7:21 a.m. |
| PD | Predicate disambiguation | batch_6a0031b5dbd081908eb0f4dbb8a0eac3 |
completed | May 10, 2026, 7:20 a.m. |
| PDg | Predicate description generation | batch_6a0031ec758c81908a3877bc19ce2701 |
completed | May 10, 2026, 7:21 a.m. |
Created at: April 29, 2026, 9 p.m.