Triple
T36977221
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FTSE/JSE Capped Indices |
E914732
|
entity |
| Predicate | primaryUseInSouthAfrica |
P10000
|
FINISHED |
| Object | benchmark for active managers |
—
|
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: benchmark for active managers | Statement: [FTSE/JSE Capped Indices, primaryUseInSouthAfrica, benchmark for active managers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryUseInSouthAfrica Context triple: [FTSE/JSE Capped Indices, primaryUseInSouthAfrica, benchmark for active managers]
-
A.
primaryUseOf
Indicates that one entity serves as the main or principal function, purpose, or application of another entity.
-
B.
primaryUseArea
Indicates the main functional area or domain in which an entity is primarily used or applied.
-
C.
usedPrimarilyIn
chosen
Indicates that something is mainly or most commonly employed within a particular context, domain, or purpose.
-
D.
primaryHumanUse
Indicates the main way humans typically use, interact with, or benefit from the referenced entity.
-
E.
widelyUsedIn
Indicates that something is commonly or extensively utilized within a particular context, domain, or group.
- 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_69f76e8d13b4819089af24a47ce092fc |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a037c8e2c648190a65fc9c7872861af |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a10036481909c71188b2a0e7f04 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:14 p.m.