Triple
T23862561
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tifone |
E592487
|
entity |
| Predicate | originLicense |
P60698
|
FINISHED |
| Object | license-built version of Daimler-Benz DB 605 |
—
|
LITERAL 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: license-built version of Daimler-Benz DB 605 | Statement: [Tifone, originLicense, license-built version of Daimler-Benz DB 605]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originLicense Context triple: [Tifone, originLicense, license-built version of Daimler-Benz DB 605]
-
A.
licenseOrigin
Indicates that one entity is the original source or issuer from which another entity’s license is derived or obtained.
-
B.
originUse
chosen
Indicates that one entity is used as the original source, basis, or starting point for the creation, derivation, or use of another entity.
-
C.
laterLicense
Indicates that one license chronologically succeeds another, coming into effect at a later time than the referenced license.
-
D.
contentLicense
Indicates the type of license or usage rights that govern how the associated content may be used, shared, or redistributed.
-
E.
oftenLicensedUnder
Indicates that an entity is frequently or commonly granted rights or permissions under a specified license.
- 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_69e25d22eb488190914b193aff952e83 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1cae16df4819081a8b3a395e45118 |
completed | April 29, 2026, 9:09 a.m. |
| PD | Predicate disambiguation | batch_69f1614a65a88190bde1efb368a151e4 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:13 p.m.