Triple
T17038311
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lysicrates Monument |
E413377
|
entity |
| Predicate | dedicatedTo |
P500
|
FINISHED |
| Object | Dionysus |
E15442
|
NE 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: Dionysus | Statement: [Lysicrates Monument, dedicatedTo, Dionysus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dionysus Context triple: [Lysicrates Monument, dedicatedTo, Dionysus]
-
A.
Dionysus
chosen
Dionysus is the ancient Greek god of wine, ecstasy, theater, and ritual madness, often linked to mystery cults and ecstatic worship.
-
B.
Dionysos
Dionysos is a suburban town in the northeastern part of the Athens metropolitan area in Greece, known for its scenic setting on the slopes of Mount Pentelicus.
-
C.
Dionysios
Dionysios is the Greek form of the name Denis, traditionally associated with Saint Denis of Paris, an early Christian martyr and bishop.
-
D.
Bacchus
Bacchus is a comic book series by Eddie Campbell that reimagines the ancient god of wine as an aging, world-weary survivor navigating modern society.
-
E.
Bacchus
Bacchus is a white wine grape variety, widely grown in Germany, known for producing aromatic, early-ripening wines often used in cool-climate regions.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d886cd18288190b006abab23f811b7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d8f45f84819092cfb27cc33da026 |
completed | April 18, 2026, 7:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a011b5b71f48190b6c865d57668b5d1 |
completed | May 10, 2026, 11:57 p.m. |
Created at: April 10, 2026, 5:33 a.m.