Triple
T1953291
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Olympia, Greece |
E42206
|
entity |
| Predicate | hasStructure |
P35
|
FINISHED |
| Object | Leonidaion |
E15443
|
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: Leonidaion | Statement: [Olympia, Greece, hasStructure, Leonidaion]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Leonidaion Context triple: [Olympia, Greece, hasStructure, Leonidaion]
-
A.
Leonidaion
chosen
Leonidaion is an ancient guesthouse complex at Olympia in Greece, built in the 4th century BCE to accommodate distinguished visitors during the Olympic Games.
-
B.
Ledaal
Ledaal is a historic manor house in Stavanger, Norway, that has served as a royal residence and cultural landmark.
-
C.
Theodosia
Theodosia is a historic port city on the southeastern coast of Crimea, known for its long history as a trading center on the Black Sea.
-
D.
Marinos
Marinos is the commonly used nickname for Yokohama F. Marinos, a prominent professional football club in Japan’s J1 League.
-
E.
Sebaste
Sebaste was an ancient city in the central highlands of Samaria, refounded and expanded by Herod the Great as a major Hellenistic-Roman urban center.
- 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_69a8870eea088190a38781990812a9bc |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb3501d108190bc5cb23f53db4411 |
completed | March 7, 2026, 5:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69adfbc611fc8190b2f512c744cbc364 |
completed | March 8, 2026, 10:44 p.m. |
Created at: March 4, 2026, 7:36 p.m.