Triple
T34311961
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary Scott, 3rd Countess of Buccleuch |
E880472
|
entity |
| Predicate | typeOfHeiress |
P197524
|
FINISHED |
| Object | landed heiress |
—
|
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: landed heiress | Statement: [Mary Scott, 3rd Countess of Buccleuch, typeOfHeiress, landed heiress]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfHeiress Context triple: [Mary Scott, 3rd Countess of Buccleuch, typeOfHeiress, landed heiress]
-
A.
hasWealthyHeiressMother
Indicates that a person has a mother who is both wealthy and an heiress.
-
B.
typeOfSuccessionRank
Indicates the specific kind or category of succession ranking that applies within a succession order or hierarchy.
-
C.
typeOfRoyalInstitution
Indicates the specific category or kind of royal institution that an entity belongs to (e.g., monarchy, royal court, royal academy).
-
D.
titleHeldAsHeiress
chosen
Indicates that a person holds a noble or hereditary title specifically in their capacity as an heiress, typically to be passed on or recognized through inheritance.
-
E.
marriedToHeiress
Indicates that a person is married to someone who is an heiress.
- 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_69f349b8bb6c8190ad12a7957a574f04 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a0124a5d7848190a6b56d18db2f661d |
completed | May 11, 2026, 12:36 a.m. |
| PD | Predicate disambiguation | batch_6a01243da1808190ada3ce553e3f55b6 |
completed | May 11, 2026, 12:35 a.m. |
Created at: May 1, 2026, 1:57 a.m.