Triple
T14151919
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Silozi |
E350703
|
entity |
| Predicate | alternateName |
P39
|
FINISHED |
| Object | Rozi |
E250947
|
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: Rozi | Statement: [Silozi, alternateName, Rozi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rozi Context triple: [Silozi, alternateName, Rozi]
-
A.
Rozi
chosen
Rozi is an alternate name for the Lozi people, a Bantu ethnic group primarily inhabiting western Zambia and known for their rich cultural traditions and historical Barotseland kingdom.
-
B.
Roz
Roz is one of the central protagonists in Margaret Atwood's novel "The Robber Bride," known for her sharp wit, business success, and complex friendship with the other women targeted by the enigmatic Zenia.
-
C.
Roz
Roz is the gruff, slug-like administrator in Pixar's "Monsters, Inc." who secretly oversees the Child Detection Agency.
-
D.
Roz
Roz is a person known primarily for her close personal relationship with Tony.
-
E.
Roz
Roz is a common shortened form of the given name Rosalind, often used as a familiar or informal nickname.
- 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_69d8278775fc8190b0802d22ca2f495d |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de6124e23481909e5132a40a1d8624 |
completed | April 14, 2026, 3:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcf7ea34408190830263d7f5a88ce9 |
completed | May 7, 2026, 8:36 p.m. |
Created at: April 10, 2026, 12:57 a.m.