Triple
T16100079
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Malcolm Ford |
E390591
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Georgia Ford |
unclear NED1
|
NE 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: Georgia Ford | Statement: [Malcolm Ford, sibling, Georgia Ford]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Georgia Ford Context triple: [Malcolm Ford, sibling, Georgia Ford]
-
A.
Georgia Ford
Georgia Ford is the daughter of acclaimed American actor Harrison Ford.
-
B.
Georgia Ford
Georgia Ford is a member of the Ford family, known as the sister of designer and entrepreneur Willard Ford.
-
C.
Germanna Ford
Germanna Ford is a historic river crossing in Virginia that played a significant role in American Civil War troop movements and campaigns.
-
D.
Benson Ford
Benson Ford was an American businessman and prominent member of the Ford family who held executive roles at Ford Motor Company in the mid-20th century.
-
E.
Karla Ford
Karla Ford is the wife of Ontario Premier Doug Ford and a relatively private figure who occasionally appears at public and political events alongside him.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide. chosen
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_69d87f198bc48190a8b7e53ca15b7ead |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e1ff6756948190a7f5ecb375e59701 |
completed | April 17, 2026, 9:37 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fffeed4e008190b1e8d924b9dc9d37 |
completed | May 10, 2026, 3:43 a.m. |
Created at: April 10, 2026, 5 a.m.