Triple
T10495974
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paddy Ashdown |
E247537
|
entity |
| Predicate | nickname |
P55
|
FINISHED |
| Object | Paddy |
E788026
|
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: Paddy | Statement: [Paddy Ashdown, nickname, Paddy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paddy Context triple: [Paddy Ashdown, nickname, Paddy]
-
A.
Paddy
chosen
Paddy is a common English diminutive form of the Irish given name Pádraig (Patrick).
-
B.
Paddie
Paddie is the given name of Paddie O'Neil, an individual likely known as an actress and entertainer.
-
C.
Seamus
Seamus is the Irish form of the given name James, commonly used for boys in Ireland and among the Irish diaspora.
-
D.
Dessie
Dessie is a significant urban center in northern Ethiopia’s Amhara Region, known as an important commercial and administrative hub.
-
E.
Dermot
Dermot is a masculine given name of Irish origin, traditionally meaning “free from envy” or “without enemy.”
- 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_69d381c309b88190af78aa681cf6a4c2 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d5098cd82c8190b44127a66c9c75ae |
completed | April 7, 2026, 1:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d8dcbafe9481908fb23cfdf150adac |
completed | April 10, 2026, 11:19 a.m. |
Created at: April 6, 2026, 12:24 p.m.