Triple
T26870614
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tremont Group feeder funds |
E676600
|
entity |
| Predicate | promisedFeature |
P162828
|
FINISHED |
| Object | consistent absolute returns |
—
|
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: consistent absolute returns | Statement: [Tremont Group feeder funds, promisedFeature, consistent absolute returns]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: promisedFeature Context triple: [Tremont Group feeder funds, promisedFeature, consistent absolute returns]
-
A.
compromiseFeature
Indicates that one entity weakens, reduces, or negatively affects the quality, effectiveness, or integrity of a feature of another entity.
-
B.
laterFeature
Indicates that one feature, event, or element occurs or is introduced after another in time.
-
C.
documentedFeature
Indicates that a feature has been formally recorded or described in documentation.
-
D.
mayIncludeFeature
Indicates that one entity is allowed or able to contain, incorporate, or be associated with a particular feature.
-
E.
protectsFeature
Indicates that one entity safeguards, preserves, or defends a particular feature or characteristic of another entity.
- F. None of above. chosen
Provenance (4 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_69f62e4168a48190b45268f922780da6 |
completed | May 2, 2026, 5:02 p.m. |
| PD | Predicate disambiguation | batch_69f62c15952881908a5ea0c25904afec |
completed | May 2, 2026, 4:53 p.m. |
| PDg | Predicate description generation | batch_69f62d5268ac8190835dc7119353b840 |
completed | May 2, 2026, 4:58 p.m. |
Created at: April 27, 2026, 5:32 a.m.