Triple
T26212588
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zen 3 |
E655526
|
entity |
| Predicate | codenameServerPlatform |
P140224
|
FINISHED |
| Object | Milan |
—
|
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: Milan | Statement: [Zen 3, codenameServerPlatform, Milan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: codenameServerPlatform Context triple: [Zen 3, codenameServerPlatform, Milan]
-
A.
servesCodename
Indicates that one entity provides or uses another entity under a specific codename or alias.
-
B.
relatedCodename
Indicates that one entity has an associated or connected codename that is contextually related to it.
-
C.
hardwareCodename
chosen
Indicates that one entity is the internal or code name assigned to a particular hardware product or component.
-
D.
codenameOwner
Indicates that one entity is the designated owner or holder of the specified codename associated with another entity.
-
E.
translationOfCodename
Indicates that one codename is a translated version of another codename, preserving its intended meaning across languages.
- F. None of above.
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_69ee5b49adb4819086545280d4ef6337 |
completed | April 26, 2026, 6:36 p.m. |
| NER | Named-entity recognition | batch_69f63fd6c68481908c542aa03e297b9c |
completed | May 2, 2026, 6:17 p.m. |
| PD | Predicate disambiguation | batch_69f63c6456608190b94e7c2e2c2a4824 |
completed | May 2, 2026, 6:03 p.m. |
Created at: April 26, 2026, 8:53 p.m.