Triple
T26870946
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Securities Investor Protection Corporation |
E676607
|
entity |
| Predicate | doesNotInsure |
P10124
|
FINISHED |
| Object | losses from market fluctuations |
—
|
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: losses from market fluctuations | Statement: [Securities Investor Protection Corporation, doesNotInsure, losses from market fluctuations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: doesNotInsure Context triple: [Securities Investor Protection Corporation, doesNotInsure, losses from market fluctuations]
-
A.
doesNotCover
chosen
Indicates that one entity fails to include, protect, or extend over another entity or area.
-
B.
doesNotProtect
Indicates that an entity fails to provide protection or safeguarding to another entity or object.
-
C.
doesNotProvideFor
Indicates that one entity fails or is not responsible for supplying support, resources, or necessary provisions to another entity.
-
D.
doesNotClaim
Indicates that an entity explicitly refrains from asserting, alleging, or taking ownership of a particular statement, right, or responsibility.
-
E.
doesNotHave
Indicates that one entity lacks, is missing, or is not in possession of another entity or attribute.
- 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_69eee9ba94bc8190b44c5d4397d04ecd |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69f6352fdb788190b9bad30243690743 |
completed | May 2, 2026, 5:32 p.m. |
| PD | Predicate disambiguation | batch_69f631850ae08190a0ba51e4f1e4ccb3 |
completed | May 2, 2026, 5:16 p.m. |
Created at: April 27, 2026, 5:32 a.m.