Triple
T26466721
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ball family of South Carolina |
E665786
|
entity |
| Predicate | notableEstateType |
P33508
|
FINISHED |
| Object | plantation |
—
|
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: plantation | Statement: [Ball family of South Carolina, notableEstateType, plantation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableEstateType Context triple: [Ball family of South Carolina, notableEstateType, plantation]
-
A.
countryEstateType
Indicates the classification or category of an estate based on the country in which it is located or to which it belongs.
-
B.
nobleEstate
Indicates that an entity is a noble’s estate or property associated with nobility.
-
C.
hasEstateType
chosen
Indicates that an entity possesses or is associated with a particular category or type of estate.
-
D.
notableLicensedProperty
Indicates that one entity is a prominent or significant intellectual property for which another entity holds an official license or usage rights.
-
E.
famousEstate
Indicates that an estate (such as a property, residence, or landholding) is widely known or renowned, typically due to its history, architecture, ownership, or cultural significance.
- 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_69ee883e812c8190a9b5a9cdb87fee5e |
completed | April 26, 2026, 9:48 p.m. |
| NER | Named-entity recognition | batch_69fec8aef1d8819094c7fd7074038e6b |
completed | May 9, 2026, 5:39 a.m. |
| PD | Predicate disambiguation | batch_69fec639876481908efd84a3631a4271 |
completed | May 9, 2026, 5:29 a.m. |
Created at: April 27, 2026, 12:16 a.m.