Triple
T38479219
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | J200 |
E915623
|
entity |
| Predicate | isPrimaryCodeFor |
P77384
|
FINISHED |
| Object | FTSE/JSE Top 40 Index |
—
|
NE NERFINISHED |
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: FTSE/JSE Top 40 Index | Statement: [J200, isPrimaryCodeFor, FTSE/JSE Top 40 Index]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isPrimaryCodeFor Context triple: [J200, isPrimaryCodeFor, FTSE/JSE Top 40 Index]
-
A.
hasPrimaryCode
chosen
Indicates that an entity is associated with its main or most important identifying code among potentially multiple codes.
-
B.
isPrimary
Indicates that one entity holds the main, leading, or most important role or status in relation to another entity or within a given context.
-
C.
isPrimarySetFor
Indicates that one entity is designated as the main or default set associated with another entity.
-
D.
primaryCode
Indicates that the referenced code is the main or most authoritative code associated with an entity, as opposed to any secondary or alternative codes.
-
E.
isOfficialCodeFor
Indicates that one entity serves as the formally recognized or authorized code that designates or identifies another entity.
- 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_69f76e8ff5cc8190a88803369183845e |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fddd373cdc8190be1b12e70e4deb1f |
completed | May 8, 2026, 12:55 p.m. |
| PD | Predicate disambiguation | batch_69fddc6915a88190ad41e379aa3ede13 |
completed | May 8, 2026, 12:51 p.m. |
Created at: May 3, 2026, 4:31 p.m.