Triple
T3905942
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Didyma |
E87204
|
entity |
| Predicate | oracleType |
P52820
|
FINISHED |
| Object | oracular sanctuary of Apollo |
—
|
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: oracular sanctuary of Apollo | Statement: [Didyma, oracleType, oracular sanctuary of Apollo]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oracleType Context triple: [Didyma, oracleType, oracular sanctuary of Apollo]
-
A.
databaseType
Indicates the specific kind or category of database technology associated with an entity.
-
B.
oreType
Indicates the specific kind or classification of ore associated with an entity.
-
C.
linkedToOracle
Indicates that one entity is connected or associated with an Oracle system, service, or resource.
-
D.
logicalType
Indicates that one entity is classified as a logical type or category used to define or constrain the logical behavior or interpretation of another entity.
-
E.
offsetType
Indicates the specific kind or category of offset applied in a relationship, such as how far or in what manner one value, position, or event is shifted relative to another.
- F. None of above. chosen
Provenance (4 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_69aed9424514819086e9c58adde6652d |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aef1abe2dc81909c18aeae9b286898 |
completed | March 9, 2026, 4:13 p.m. |
| PD | Predicate disambiguation | batch_69aee75cff148190b6d5979d17fae085 |
completed | March 9, 2026, 3:29 p.m. |
| PDg | Predicate description generation | batch_69aef1aada308190821a3dfa6af170b3 |
completed | March 9, 2026, 4:13 p.m. |
Created at: March 9, 2026, 3:22 p.m.