Triple
T6045880
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Temple of Poseidon at Isthmia |
E134664
|
entity |
| Predicate | worshippedDeityRole |
P10015
|
FINISHED |
| Object | god of the sea |
—
|
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: god of the sea | Statement: [Temple of Poseidon at Isthmia, worshippedDeityRole, god of the sea]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: worshippedDeityRole Context triple: [Temple of Poseidon at Isthmia, worshippedDeityRole, god of the sea]
-
A.
worshippedAs
Indicates that one entity is regarded and treated with religious reverence or devotion by another entity.
-
B.
worshipedAs
chosen
Indicates that one entity regards and treats another as a deity or sacred figure, offering reverence, devotion, or religious honor.
-
C.
servedDeity
Indicates that one entity acted in service, devotion, or worship toward a particular deity.
-
D.
worshipsDeity
Indicates that one entity reveres, honors, or performs religious devotion toward another entity regarded as a deity.
-
E.
typeOfDeity
Indicates that one entity is classified as a specific kind or category of deity in relation to another.
- 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_69c00876a69881908088a2626d3b2666 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c056e53f508190864be04bc016c525 |
completed | March 22, 2026, 8:53 p.m. |
| PD | Predicate disambiguation | batch_69c049eb52a08190ac10fd703735f5aa |
completed | March 22, 2026, 7:58 p.m. |
Created at: March 22, 2026, 4:09 p.m.