Triple
T1373469
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elizabeth Browning Donner |
E30165
|
entity |
| Predicate | positionInSpouseOrder |
P4764
|
FINISHED |
| Object | second wife of Elliott Roosevelt |
—
|
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: second wife of Elliott Roosevelt | Statement: [Elizabeth Browning Donner, positionInSpouseOrder, second wife of Elliott Roosevelt]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionInSpouseOrder Context triple: [Elizabeth Browning Donner, positionInSpouseOrder, second wife of Elliott Roosevelt]
-
A.
spouseOrder
chosen
Indicates the position or sequence of a person among multiple spouses in a marital relationship.
-
B.
positionOnMarriage
Indicates a person's stance, opinion, or policy regarding the institution or practice of marriage.
-
C.
positionHeldBySpouse
Indicates that a particular position, role, or office is or was held by the spouse of a given person.
-
D.
positionInFamilyBirthOrder
Indicates the relative order in which a person was born within their family (e.g., first-born, middle child, last-born).
-
E.
coSpouse
Indicates that two individuals are married to each other as spouses.
- 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_69a498f912008190a376a98b207b2071 |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c2f660888190bc9240e0dc4f0aa3 |
completed | March 1, 2026, 10:51 p.m. |
| PD | Predicate disambiguation | batch_69a4befcabdc8190a9f05d002603f81c |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:57 p.m.