Triple
T30018831
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lions of Delos |
E762673
|
entity |
| Predicate | hasReplicaLocation |
P74022
|
FINISHED |
| Object | original terrace on Delos |
—
|
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: original terrace on Delos | Statement: [Lions of Delos, hasReplicaLocation, original terrace on Delos]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasReplicaLocation Context triple: [Lions of Delos, hasReplicaLocation, original terrace on Delos]
-
A.
replicaLocation
chosen
Indicates the physical or logical place where a copy or replica of an item, resource, or data set is stored or maintained.
-
B.
hasReplicaStatus
Indicates that one entity serves as a copy or duplicate of another, often with a specific role or state in a replication relationship.
-
C.
hasReplicaPolicy
Indicates that an entity is associated with a specific policy governing how its replicas are created, managed, or maintained.
-
D.
hasReplicationPartner
Indicates that an entity participates in a replication process with another entity, designating the other as its replication counterpart or partner.
-
E.
hasReplicationNumber
Indicates that an entity is associated with a specific replication or copy number, typically quantifying how many instances or reproductions of it exist.
- 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_69f2246b0c84819094f1250b6a02d277 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_6a0048697bd081909073640666ca6a96 |
completed | May 10, 2026, 8:57 a.m. |
| PD | Predicate disambiguation | batch_6a0047bf3c248190a9ac97a7afdfe2cb |
completed | May 10, 2026, 8:54 a.m. |
Created at: April 29, 2026, 6:46 p.m.