Triple
T511537
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | James Roosevelt Roosevelt |
E10619
|
entity |
| Predicate | siblingRelationship |
P363
|
FINISHED |
| Object | half-brother of Franklin D. 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: half-brother of Franklin D. Roosevelt | Statement: [James Roosevelt Roosevelt, siblingRelationship, half-brother of Franklin D. Roosevelt]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: siblingRelationship Context triple: [James Roosevelt Roosevelt, siblingRelationship, half-brother of Franklin D. Roosevelt]
-
A.
sibling
chosen
Indicates that two entities share at least one parent, making them brothers or sisters to each other.
-
B.
hasFamilialTieTo
Indicates a relationship where two entities are connected by family bonds, such as by blood, marriage, or adoption.
-
C.
historicalRelationship
Indicates a relationship that existed between entities in the past, often tied to a specific historical period, context, or event.
-
D.
isNephewOf
Indicates that one person is the male child of another person's sibling.
-
E.
relationshipType
Indicates the specific kind of relationship that exists between two or more entities.
- 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_69a2e84a0d08819087e01863fcd9abf1 |
completed | Feb. 28, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69a2f16768c081909d05537ff070868b |
completed | Feb. 28, 2026, 1:45 p.m. |
| PD | Predicate disambiguation | batch_69a2edff001c81909182a7e26c6dc51b |
completed | Feb. 28, 2026, 1:30 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.