Triple
T11912006
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Exchange-traded fund |
E283418
|
entity |
| Predicate | usuallyHas |
P39152
|
FINISHED |
| Object | lower expense ratio than mutual fund |
—
|
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: lower expense ratio than mutual fund | Statement: [Exchange-traded fund, usuallyHas, lower expense ratio than mutual fund]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usuallyHas Context triple: [Exchange-traded fund, usuallyHas, lower expense ratio than mutual fund]
-
A.
usuallyAccompaniedBy
Indicates that one entity is commonly or habitually found together with, or occurs in the presence of, another entity.
-
B.
typicallyHolds
chosen
Indicates that a certain relationship or condition generally holds true in typical or normal situations, though not necessarily in all cases.
-
C.
usuallyFrom
Indicates that something typically originates, is derived, or comes from a particular source or location.
-
D.
usuallyHears
Indicates that one entity typically or habitually perceives sounds produced by another entity.
-
E.
actuallyDoes
Indicates that an entity truly performs or carries out a specified action or behavior, as opposed to merely being expected, claimed, or assumed to do so.
- 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_69d6ab2c07e88190ba13b0d21fd6cf33 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8e528f6748190ac873a040a61fa93 |
completed | April 10, 2026, 11:55 a.m. |
| PD | Predicate disambiguation | batch_69d8bb3632ac8190b13e53c2b5db7125 |
completed | April 10, 2026, 8:56 a.m. |
Created at: April 8, 2026, 9:44 p.m.