Triple
T1509505
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Patrick J. Kennedy |
E33981
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Patrick |
E149608
|
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: Patrick | Statement: [Patrick J. Kennedy, givenName, Patrick]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Patrick Context triple: [Patrick J. Kennedy, givenName, Patrick]
-
A.
Patrick
Patrick is a component or constituent part of something associated with or named Kirkpatrick.
-
B.
Patrick
chosen
Patrick is the given first name of Pat Riley, the famed American basketball coach and executive.
-
C.
Philip
Philip is the given first name of the renowned British actor Basil Rathbone, best known for his definitive film portrayals of Sherlock Holmes.
-
D.
Philip
Philip is the middle name of George Philip Wells, the zoologist son of author H. G. Wells.
-
E.
Philip
Philip is the given name of Philip Barton Key II, the 19th-century U.S. Attorney for the District of Columbia whose 1859 murder by Congressman Daniel Sickles became a landmark legal case.
- 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_69a885f352a4819099b24ff15489dede |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a8891daf708190a23d6c920eac8b6d |
completed | March 4, 2026, 7:33 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad51a8b8b88190a320071964846518 |
completed | March 8, 2026, 10:38 a.m. |
Created at: March 4, 2026, 7:24 p.m.