Triple
T5549945
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Freddie Bartholomew |
E145500
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Lord Jeff |
E78189
|
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: Lord Jeff | Statement: [Freddie Bartholomew, notableWork, Lord Jeff]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lord Jeff Context triple: [Freddie Bartholomew, notableWork, Lord Jeff]
-
A.
Lord Jeff
chosen
Lord Jeff is the former, now-retired mascot of Amherst College, based on Lord Jeffery Amherst, whose controversial legacy led the school to abandon the character.
-
B.
Lord Hodge
Lord Hodge is a senior Scottish jurist who serves as Deputy President of the Supreme Court of the United Kingdom.
-
C.
Sir Harry
Sir Harry is a chivalrous yet comically earnest knight and suitor in the musical comedy "Once Upon a Mattress."
-
D.
Guy Mannering
Guy Mannering is a historical novel by Sir Walter Scott that blends romance, adventure, and Scottish local color in a tale of lost heirs, family secrets, and fortune-telling.
-
E.
Sir Carter
Sir Carter is one of Beyoncé and Jay-Z's twin children, born in 2017.
- 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_69c008fb879c81909f5bfa56fadc1d46 |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c01fe2aef481909944bc582c1f67a4 |
completed | March 22, 2026, 4:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c0283101dc8190a52ef2edbb523e78 |
completed | March 22, 2026, 5:34 p.m. |
Created at: March 22, 2026, 3:35 p.m.