Triple
T9105843
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bob Ford |
E218475
|
entity |
| Predicate | nickname |
P55
|
FINISHED |
| Object | Bob Ford |
E218475
|
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: Bob Ford | Statement: [Bob Ford, nickname, Bob Ford]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bob Ford Context triple: [Bob Ford, nickname, Bob Ford]
-
A.
Bob Ford
chosen
Bob Ford was the outlaw and gang member historically known for killing the infamous American bandit Jesse James.
-
B.
Thomas Ford
Thomas Ford was an American politician who served as the eighth governor of Illinois from 1842 to 1846.
-
C.
Sam Ford
Sam Ford is the son of Nathan Ford, the central mastermind character from the television series "Leverage."
-
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.
Jack Ford
Jack Ford is the nickname of John Ford, the legendary American film director renowned for his influential Westerns and multiple Academy Awards.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca83db7448819090d0a5de842ef2ac |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cca57286a88190b256d2461c5c0aed |
completed | April 1, 2026, 4:56 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d01840d2488190a14d458aa181cc47 |
completed | April 3, 2026, 7:42 p.m. |
Created at: March 30, 2026, 7:16 p.m.