Triple
T9257094
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lord Shelburne |
E222471
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Petty |
E109028
|
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: Petty | Statement: [Lord Shelburne, familyName, Petty]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Petty Context triple: [Lord Shelburne, familyName, Petty]
-
A.
Petty
chosen
Petty is the surname of Tom Petty, the influential American rock musician and frontman of Tom Petty and the Heartbreakers.
-
B.
Meek
Meek is a surname of Scottish origin borne by various notable individuals across fields such as acting, music, and politics.
-
C.
Petty Cury
Petty Cury is a historic pedestrianised shopping street in the centre of Cambridge, England.
-
D.
Petit
Petit is the surname of Sir Dinshaw Maneckji Petit, 1st Baronet, a prominent 19th-century Parsi industrialist and philanthropist from Bombay.
-
E.
Sucker
Sucker is a 2015 Australian comedy film about a teenage conman who becomes entangled with a charismatic swindler and his enigmatic daughter.
- 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_69ca841e4cd481908e738c74e958eaea |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd06b4e2048190af0d65b904677c36 |
completed | April 1, 2026, 11:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d09be75fd88190b6e99b0884dcc14c |
completed | April 4, 2026, 5:04 a.m. |
Created at: March 30, 2026, 7:32 p.m.