Triple
T36748605
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Abigail Johnson |
E907841
|
entity |
| Predicate | sharesOwnership |
P3498
|
FINISHED |
| Object | Fidelity Investments |
—
|
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: Fidelity Investments | Statement: [Abigail Johnson, sharesOwnership, Fidelity Investments]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharesOwnership Context triple: [Abigail Johnson, sharesOwnership, Fidelity Investments]
-
A.
sharesOwnershipWith
chosen
Indicates that two or more entities jointly hold ownership rights or stakes in the same asset, resource, or organization.
-
B.
sharesCustodyWith
Indicates that two or more parties jointly hold legal responsibility and decision-making authority for the care and upbringing of the same dependent, typically a child.
-
C.
privateOwnershipShare
Indicates the proportion or share of ownership in an entity that is held by private (non-governmental) owners.
-
D.
sharesWith
Indicates that one entity gives another entity access to or use of something it possesses.
-
E.
sharesOwnershipStructureWith
Indicates that two entities have the same or closely aligned ownership structure, such as sharing the same owners, parent company, or control hierarchy.
- 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_69f76e76d10881909ec1679bc043108c |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a009f53a4948190aef4ede1713e1748 |
completed | May 10, 2026, 3:08 p.m. |
| PD | Predicate disambiguation | batch_6a009edc53d4819080b22c1074a990f3 |
completed | May 10, 2026, 3:06 p.m. |
Created at: May 3, 2026, 4:12 p.m.