Triple
T29184367
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Miss Mary Shepherd |
E739824
|
entity |
| Predicate | housingSituation |
P75
|
FINISHED |
| Object | lives in a van parked on Alan Bennett’s property |
—
|
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: lives in a van parked on Alan Bennett’s property | Statement: [Miss Mary Shepherd, housingSituation, lives in a van parked on Alan Bennett’s property]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: housingSituation Context triple: [Miss Mary Shepherd, housingSituation, lives in a van parked on Alan Bennett’s property]
-
A.
hasHousingArrangement
Indicates that an entity has a specific type or status of housing or living arrangement in relation to another entity or context.
-
B.
hasHousingAccess
Indicates that an entity has the ability, right, or opportunity to obtain or use suitable housing.
-
C.
housingPattern
Indicates the typical arrangement or distribution of housing units or residential structures within a given area or context.
-
D.
residence
chosen
Indicates that one entity lives at, is based in, or habitually occupies the location represented by the other entity.
-
E.
habitation
Indicates that one entity serves as the dwelling place, residence, or living environment for another entity.
- 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_69f07cb74c2c8190ad396487fcb4fde6 |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_69f66385d3a081908460881857d43322 |
completed | May 2, 2026, 8:50 p.m. |
| PD | Predicate disambiguation | batch_69f65c24f8b48190af81b575f3c15be5 |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 11:59 a.m.