Triple
T20615277
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FIGI |
E506548
|
entity |
| Predicate | relationshipToOtherIdentifiers |
P33159
|
FINISHED |
| Object | can be mapped to ISIN |
—
|
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: can be mapped to ISIN | Statement: [FIGI, relationshipToOtherIdentifiers, can be mapped to ISIN]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipToOtherIdentifiers Context triple: [FIGI, relationshipToOtherIdentifiers, can be mapped to ISIN]
-
A.
relatedIdentity
Indicates that two identities are connected or associated with each other in some meaningful way, such as being alternate, linked, or otherwise contextually related.
-
B.
relatedIdentifier
chosen
Indicates that one identifier is associated with another identifier that refers to the same or a related entity in a different context or system.
-
C.
relationToCurie
Indicates a relational connection or association that one entity has specifically with Curie.
-
D.
identityRelation
Indicates that two entities are in fact the very same entity, not merely similar or equivalent.
-
E.
externalRelations
Indicates that an entity has relationships, interactions, or connections with entities outside its own immediate group, system, or organization.
- 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_69e0b4bc90988190ac360aaf645efc1d |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6aadaf47881909e93efb535c6c1e3 |
completed | April 20, 2026, 10:38 p.m. |
| PD | Predicate disambiguation | batch_69e5a00c43308190b7ea58d559257e07 |
completed | April 20, 2026, 3:39 a.m. |
Created at: April 16, 2026, 11:41 a.m.