Triple
T10134124
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FTSE:ASX |
E226811
|
entity |
| Predicate | underlyingIndexFor |
P5158
|
FINISHED |
| Object | index funds |
—
|
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: index funds | Statement: [FTSE:ASX, underlyingIndexFor, index funds]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: underlyingIndexFor Context triple: [FTSE:ASX, underlyingIndexFor, index funds]
-
A.
associatedIndex
chosen
Indicates that one entity is linked to another through a corresponding index or positional reference.
-
B.
isReferenceIndexFor
Indicates that one entity serves as an index or pointer used to locate, identify, or access another entity.
-
C.
knownCompositeForIndex
Indicates that a given value is recognized as a composite number corresponding to a particular index in a sequence or data structure.
-
D.
hasBaseIndex
Indicates that one entity serves as the reference or starting index from which another entity’s position, offset, or ordering is calculated.
-
E.
coreIndex
Indicates the position or identifier of an entity within a central or primary ordered structure (its core sequence or index).
- 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_69ca8433ec308190b8b25a6fe359c34c |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cdd33808048190b6023a6cd83fc179 |
completed | April 2, 2026, 2:23 a.m. |
| PD | Predicate disambiguation | batch_69cd4ba4f5d88190ba68e63be10b08c7 |
completed | April 1, 2026, 4:45 p.m. |
Created at: March 30, 2026, 9:06 p.m.