Triple
T31862893
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bananarama |
E813377
|
entity |
| Predicate | replacedMemberWith |
P27992
|
FINISHED |
| Object | Siobhan Fahey |
—
|
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: Siobhan Fahey | Statement: [Bananarama, replacedMemberWith, Siobhan Fahey]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: replacedMemberWith Context triple: [Bananarama, replacedMemberWith, Siobhan Fahey]
-
A.
replacementMember
chosen
Indicates that one entity serves as a substitute or successor taking over the role, position, or function previously held by another entity.
-
B.
replacedWith
Indicates that one entity has been substituted or superseded by another entity, taking over its role, function, or position.
-
C.
placedBy
Indicates that one entity was positioned, set, or put in a location or context by another entity.
-
D.
replacesComponentOf
Indicates that one entity takes the place of a specific component within another entity, substituting for that component in its role or function.
-
E.
roleReplacedOn
Indicates that one role has been substituted or taken over by another role at a specific point in time.
- 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_69f348ebf32881908d9439646933dc76 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69fd35d108908190b79b1e8e6bbd62aa |
completed | May 8, 2026, 1:01 a.m. |
| PD | Predicate disambiguation | batch_69fd34cb46108190b43c3b7f67ec4cd4 |
completed | May 8, 2026, 12:56 a.m. |
Created at: April 30, 2026, 11:53 p.m.