Triple
T3819748
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harrison Ford |
E84343
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object |
Georgia Ford
Georgia Ford is the daughter of acclaimed American actor Harrison Ford.
|
E390592
|
NE FINISHED |
How this triple was built (4 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: [Harrison Ford, child, Georgia Ford]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Georgia Ford Context triple: [Harrison Ford, child, Georgia Ford]
-
A.
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.
-
B.
Charlotte Ford
Charlotte Ford is an American heiress and socialite, known as a prominent member of the wealthy and influential Ford automotive family.
-
C.
Lisa Vanderzee Ford
Lisa Vanderzee Ford is the wife of Ford Motor Company executive chairman William Clay Ford Jr.
-
D.
Edward Charles Ford
Edward Charles Ford, better known as Whitey Ford, was a Hall of Fame left-handed pitcher who starred for the New York Yankees in the 1950s and 1960s.
-
E.
Martha Firestone Ford
Martha Firestone Ford is an American businesswoman and principal owner of the NFL's Detroit Lions, known for her leadership of the franchise following the death of her husband William Clay Ford Sr.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Georgia Ford Triple: [Harrison Ford, child, Georgia Ford]
Generated description
Georgia Ford is the daughter of acclaimed American actor Harrison Ford.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Georgia Ford Target entity description: Georgia Ford is the daughter of acclaimed American actor Harrison Ford.
-
A.
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.
-
B.
Charlotte Ford
Charlotte Ford is an American heiress and socialite, known as a prominent member of the wealthy and influential Ford automotive family.
-
C.
Lisa Vanderzee Ford
Lisa Vanderzee Ford is the wife of Ford Motor Company executive chairman William Clay Ford Jr.
-
D.
Edward Charles Ford
Edward Charles Ford, better known as Whitey Ford, was a Hall of Fame left-handed pitcher who starred for the New York Yankees in the 1950s and 1960s.
-
E.
Martha Firestone Ford
Martha Firestone Ford is an American businesswoman and principal owner of the NFL's Detroit Lions, known for her leadership of the franchise following the death of her husband William Clay Ford Sr.
- F. None of above. chosen
Provenance (5 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_69aed931f5908190be2c07af66d4df25 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeea601d408190b09dc486e77488d4 |
completed | March 9, 2026, 3:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4fb466a108190ac203ee00ce58f04 |
completed | March 14, 2026, 6:08 a.m. |
| NEDg | Description generation | batch_69b4fc08d65081908953482b10fa5611 |
completed | March 14, 2026, 6:11 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b4fc7d8cf081909c4447818b5363c5 |
completed | March 14, 2026, 6:13 a.m. |
Created at: March 9, 2026, 3:17 p.m.