Triple
T2414063
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Victor Verster Prison |
E52261
|
entity |
| Predicate | MandelaAccommodationType |
P542
|
FINISHED |
| Object | separate house on prison grounds |
—
|
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: separate house on prison grounds | Statement: [Victor Verster Prison, MandelaAccommodationType, separate house on prison grounds]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: MandelaAccommodationType Context triple: [Victor Verster Prison, MandelaAccommodationType, separate house on prison grounds]
-
A.
hotelCategory
Indicates the classification or rating level assigned to a hotel (e.g., star rating or category tier).
-
B.
hasAccommodation
Indicates that an entity provides, owns, or is associated with a place for someone to stay or live.
-
C.
reservationLocatedIn
Indicates that a reservation (such as a booking or held resource) is situated within or associated with a specific location or place.
-
D.
residenceType
chosen
Indicates the kind or category of dwelling or living arrangement associated with an entity.
-
E.
hotelClass
Indicates the classification or rating level assigned to a hotel, such as its star category or quality tier.
- 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_69ab495622948190bc6bc6e4cddaf645 |
completed | March 6, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69abc94a6458819087b8c4fe81a2d031 |
completed | March 7, 2026, 6:44 a.m. |
| PD | Predicate disambiguation | batch_69abc5a6cbd0819086c0716e266b7ebb |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 6, 2026, 9:41 p.m.