Triple
T7097667
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paul McGrath |
E165372
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | McGrath |
E480137
|
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: McGrath | Statement: [Paul McGrath, familyName, McGrath]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: McGrath Context triple: [Paul McGrath, familyName, McGrath]
-
A.
McGrath
chosen
McGrath is a surname of Irish origin, closely related to and sometimes used as a variant of the surname McGraw.
-
B.
McKernan
McKernan is the surname of Ron "Pigpen" McKernan, the influential founding keyboardist and vocalist of the Grateful Dead.
-
C.
Keoghan
Keoghan is an Irish surname most prominently associated with actor Barry Keoghan, known for his roles in films such as "The Banshees of Inisherin" and "Dunkirk."
-
D.
Maginnes
Maginnes is the maiden surname of Nancy Maginnes Kissinger, an American philanthropist and the wife of former U.S. Secretary of State Henry Kissinger.
-
E.
McGillis
McGillis is a surname most notably associated with American actress Kelly McGillis, known for her roles in films such as "Top Gun" and "Witness."
- 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_69c6887e8c10819091cee237560d32da |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e5561dd08190be6b784754a0c1bc |
completed | March 27, 2026, 8:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c79ca2be7c8190b5a8c6f2c64a0d8d |
completed | March 28, 2026, 9:17 a.m. |
Created at: March 27, 2026, 2:42 p.m.