Triple
T23764273
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | VOLV A |
E587333
|
entity |
| Predicate | hasShareClassSibling |
P42346
|
FINISHED |
| Object | VOLV B |
—
|
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: VOLV B | Statement: [VOLV A, hasShareClassSibling, VOLV B]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasShareClassSibling Context triple: [VOLV A, hasShareClassSibling, VOLV B]
-
A.
hasShareClassRelationshipWith
chosen
Indicates a relationship where two financial instruments or entities are connected through a specific share class structure or classification.
-
B.
hasShareClass
Indicates that an entity is associated with a specific class or category of shares that defines distinct rights or characteristics of ownership.
-
C.
hasSiblingMembers
Indicates that two entities are members of a group or organization and are siblings to each other within that membership context.
-
D.
hasSiblingAspect
Indicates that one entity possesses a characteristic, feature, or aspect that is conceptually parallel or analogous to a corresponding aspect of another entity, as in a sibling-like relationship between their attributes.
-
E.
hasSiblingTier
Indicates that two entities occupy the same or equivalent sibling level or rank within a hierarchical 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_69e2490b8ac48190a6b35f1d5500486b |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1bdb4e9248190b64b063637b66702 |
completed | April 29, 2026, 8:13 a.m. |
| PD | Predicate disambiguation | batch_69f155f79e34819080f9ddb972b34deb |
completed | April 29, 2026, 12:51 a.m. |
Created at: April 17, 2026, 7:15 p.m.