Triple
T3033653
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Magique |
E82954
|
entity |
| Predicate | followedBy |
P78
|
FINISHED |
| Object | Cobi |
E133619
|
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: Cobi | Statement: [Magique, followedBy, Cobi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cobi Context triple: [Magique, followedBy, Cobi]
-
A.
Cobi
chosen
Cobi is the cubist-style Catalan sheepdog character that served as the official mascot of the 1992 Barcelona Summer Olympics.
-
B.
Kiko
Kiko is the young, albino giant ape who serves as the gentle offspring and companion of King Kong in the 1933 film "Son of Kong."
-
C.
Banzi
Banzi is a town in the Basilicata region of southern Italy, known as the modern site near the ancient Lucanian city of Bantia.
-
D.
Koopie Koo
Koopie Koo is a minor character in the Paper Mario series, known as Koops' affectionate and supportive Koopa girlfriend from his hometown.
-
E.
Bubi
Bubi is a Bantu language spoken by the Bubi people, primarily on Bioko Island in Equatorial Guinea.
- 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_69ad8b21a62881908ec5dd4fba4a187c |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9af13ce48190bda4f5ca0ffe6285 |
completed | March 8, 2026, 3:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b1dec30d8081909d6ee691e5e51434 |
completed | March 11, 2026, 9:29 p.m. |
Created at: March 8, 2026, 3:01 p.m.