Triple
T16472493
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DKMS |
E400098
|
entity |
| Predicate | hadLocalBranchesIn |
P73566
|
FINISHED |
| Object | schools in Bulgaria |
—
|
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: schools in Bulgaria | Statement: [DKMS, hadLocalBranchesIn, schools in Bulgaria]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadLocalBranchesIn Context triple: [DKMS, hadLocalBranchesIn, schools in Bulgaria]
-
A.
hadBranchIn
chosen
Indicates that an organization or entity maintained a branch, office, or subsidiary located in another specified place or entity.
-
B.
hasFormerBranchConnection
Indicates a relationship where two entities were previously connected through a branch affiliation that no longer exists.
-
C.
hasBranchName
Indicates that an entity (such as a branch or subdivision) bears or is identified by a specific branch name.
-
D.
hasBranches
Indicates that an entity extends into multiple subordinate parts or offshoots, like limbs, divisions, or sections stemming from a main source.
-
E.
presentInBranch
Indicates that something exists or is available within a specific branch or subdivision of a larger organization or structure.
- 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_69d87f2dac988190b74d6e185fa88ba4 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e32dd19df881909e4562a5e8473338 |
completed | April 18, 2026, 7:08 a.m. |
| PD | Predicate disambiguation | batch_69e22706b0588190a48a951c5211a617 |
completed | April 17, 2026, 12:26 p.m. |
Created at: April 10, 2026, 5:11 a.m.