Triple
T35705618
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Credit Dauphine |
E1031710
|
entity |
| Predicate | operatesAsFrontFor |
P130301
|
FINISHED |
| Object | SD-6 |
—
|
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: SD-6 | Statement: [Credit Dauphine, operatesAsFrontFor, SD-6]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatesAsFrontFor Context triple: [Credit Dauphine, operatesAsFrontFor, SD-6]
-
A.
operatedOnFront
Indicates that an action or operation was performed specifically on the front side or front-facing part of an entity.
-
B.
operatedAs
Indicates that an entity functioned or was used in the capacity, role, or identity of another entity for some period of time.
-
C.
frontOf
Indicates that one entity is positioned directly before another along a primary viewing or movement direction.
-
D.
formerOperates
Indicates that an entity previously operated or managed another entity but no longer does so.
-
E.
frontEndFor
chosen
Indicates that one entity serves as the user-facing interface or access point through which another underlying system, service, or component is used or interacted with.
- 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_69f76e0d393c8190b6303c64408736db |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a017bc21b048190b9c680013de203b6 |
completed | May 11, 2026, 6:48 a.m. |
| PD | Predicate disambiguation | batch_6a017aa09c4481909c3b55e0cd13501e |
completed | May 11, 2026, 6:43 a.m. |
Created at: May 3, 2026, 4:05 p.m.