Triple
T3793821
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hyacinthus |
E89720
|
entity |
| Predicate | origin |
P410
|
FINISHED |
| Object | Sparta |
E56539
|
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: Sparta | Statement: [Hyacinthus, origin, Sparta]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sparta Context triple: [Hyacinthus, origin, Sparta]
-
A.
Sparta
chosen
Sparta was a prominent ancient Greek city-state known for its militaristic society, rigorous citizen training, and dominant land-based army.
-
B.
Athens and Sparta
Athens and Sparta were the two leading city-states of ancient Greece, renowned for their contrasting democratic and militaristic societies and their rivalry during the Peloponnesian War.
-
C.
Argolid
Argolid is a historic region in the northeastern Peloponnese of Greece, renowned as the heartland of several major Bronze Age and classical Greek centers.
-
D.
Hieria
Hieria was an imperial suburb of Constantinople on the Asian shore of the Bosporus, known as the site of the 8th-century iconoclastic Council of Hieria.
-
E.
Arcádia
Arcádia was a Portuguese publishing house known for releasing influential literary and political works in the mid-20th century.
- 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_69aed9597d6881909b6ee3b9de859223 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aee76b809c81908312f308fbe85bf4 |
completed | March 9, 2026, 3:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4f05c0f908190b5638e75b06dab4d |
completed | March 14, 2026, 5:21 a.m. |
Created at: March 9, 2026, 3:15 p.m.