Triple
T5842092
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deutsche Börse |
E129616
|
entity |
| Predicate | hasBusinessDivision |
P7588
|
FINISHED |
| Object | Clearstream |
E129623
|
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: Clearstream | Statement: [Deutsche Börse, hasBusinessDivision, Clearstream]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Clearstream Context triple: [Deutsche Börse, hasBusinessDivision, Clearstream]
-
A.
Clearstream
chosen
Clearstream is a major European post-trade services provider and international central securities depository that handles the settlement and custody of securities.
-
B.
Ripple
"Ripple" is a beloved folk-influenced ballad by the Grateful Dead, known for its gentle melody, spiritual lyrics, and enduring sing-along chorus.
-
C.
Ripple
Ripple is a small village in the Dover District of Kent, England, known for its rural character and historic parish church.
-
D.
Z-Money
Z-Money is a hip-hop artist and collaborator known for working closely with Chicago rapper Valee.
-
E.
Clipper
Clipper is a reloadable contactless smart card system used for paying fares on public transit across the San Francisco Bay Area.
- 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_69c0084bd31c8190a796bb6284845e83 |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c034d876fc819089818c731116af56 |
completed | March 22, 2026, 6:28 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c0bfce88f88190bbc78ce9c7c3c107 |
completed | March 23, 2026, 4:21 a.m. |
Created at: March 22, 2026, 3:54 p.m.