Triple
T19646530
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Squire Gresham |
E471685
|
entity |
| Predicate | estateCondition |
P34351
|
FINISHED |
| Object | declining |
—
|
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: declining | Statement: [Squire Gresham, estateCondition, declining]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: estateCondition Context triple: [Squire Gresham, estateCondition, declining]
-
A.
estateCharacteristic
Indicates that an estate possesses a particular attribute, quality, or defining feature.
-
B.
propertyStatus
chosen
Indicates the current condition, state, or classification assigned to a property within a given context (e.g., availability, legal standing, or operational state).
-
C.
estateVariantName
Indicates that one name is an alternative or variant designation used for the same estate.
-
D.
estate
Indicates a legal or ownership relationship in which a person or entity holds rights, interests, or control over property or assets.
-
E.
homeStatus
Indicates the current condition or state of a home in relation to a specified context (such as occupancy, availability, or operational status).
- 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_69d8e51395348190ac1416d46dfc6db0 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e64125dd9481908a891c71c975a964 |
completed | April 20, 2026, 3:07 p.m. |
| PD | Predicate disambiguation | batch_69e514e941008190898d978d7bde91e4 |
completed | April 19, 2026, 5:46 p.m. |
Created at: April 10, 2026, 1:44 p.m.