Triple
T11150918
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sebastian Coe |
E263780
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Coe |
E263780
|
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: Coe | Statement: [Sebastian Coe, familyName, Coe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Coe Context triple: [Sebastian Coe, familyName, Coe]
-
A.
Coe
chosen
Coe is a surname most prominently associated with Sebastian Coe, the British middle-distance running champion and influential sports administrator.
-
B.
Coën
Coën is a surname or given name variant of "Coen," often of Dutch origin and sometimes written with a diaeresis to clarify pronunciation.
-
C.
Cozz
Cozz is an American rapper from Los Angeles known for his introspective lyricism and for being signed to J. Cole’s Dreamville Records.
-
D.
Coy
Coy is a given name that can be used for individuals of any gender, often appearing in English-speaking contexts.
-
E.
Keos
Keos is the ancient Greek name for the Aegean island now known as Kea, part of the Cyclades archipelago.
- 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_69d6aa9ccddc8190868998c8b7beb060 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e8719e74819095413abc6c79296c |
completed | April 9, 2026, 5:57 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e4422ca62c81909a3a935fb7e28c34 |
completed | April 19, 2026, 2:47 a.m. |
Created at: April 8, 2026, 9:28 p.m.