Triple
T20855403
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ajax |
E513465
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | Atlas |
—
|
NE NERFINISHED |
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: Atlas | Statement: [Ajax, hasVariant, Atlas]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Atlas Context triple: [Ajax, hasVariant, Atlas]
-
A.
Atlas
chosen
Atlas is a Titan from Greek mythology best known for bearing the weight of the heavens on his shoulders as punishment from the gods.
-
B.
Atlas
Atlas is a family of American expendable launch vehicles originally developed from a ballistic missile program and widely used to place satellites and spacecraft into orbit.
-
C.
Atlas
Atlas is a professional Mexican football club based in Guadalajara, Jalisco, known for its historic presence in Liga MX.
-
D.
Atlas
Atlas is a monumental ongoing project by German artist Gerhard Richter, consisting of thousands of photographs, sketches, and collages that document and inform his artistic practice.
-
E.
Atlas
Atlas is one of the two cooperative testing robots in the puzzle-platform video game Portal 2, known for assisting in solving test chambers designed by GLaDOS.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4f5b01081909452f654d2fc3f50 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c3a81ac4819084a07625b8ed4ec5 |
completed | April 21, 2026, 12:24 a.m. |
Created at: April 16, 2026, 12:44 p.m.