Triple
T18261019
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dursley family (Harry Potter film series) |
E437352
|
entity |
| Predicate | wardSleepingPlace |
P17054
|
FINISHED |
| Object | cupboard under the stairs (early films) |
—
|
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: cupboard under the stairs (early films) | Statement: [Dursley family (Harry Potter film series), wardSleepingPlace, cupboard under the stairs (early films)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wardSleepingPlace Context triple: [Dursley family (Harry Potter film series), wardSleepingPlace, cupboard under the stairs (early films)]
-
A.
laidDownPlace
Indicates the location where an entity was laid down or placed.
-
B.
bedLocation
Indicates the spatial position or placement of a bed relative to its surrounding environment or reference objects.
-
C.
sunkPlace
Indicates that one entity caused another (typically a vessel or structure) to sink at a specific location.
-
D.
beds
chosen
Indicates that one entity provides or designates a place for another entity to sleep or rest.
-
E.
nestLocation
Indicates the place or environment where an animal or organism builds or maintains its nest.
- 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_69d8b913351c8190932b6a426de04b41 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4ff7591b4819083f2b29d60298747 |
completed | April 19, 2026, 4:14 p.m. |
| PD | Predicate disambiguation | batch_69e44fcdee748190bae6fb76e0cb22f3 |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:34 a.m.