Triple
T3027944
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ion |
E82824
|
entity |
| Predicate | grandfather |
P979
|
FINISHED |
| Object | Hellen |
E102205
|
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: Hellen | Statement: [Ion, grandfather, Hellen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hellen Context triple: [Ion, grandfather, Hellen]
-
A.
Hellen
chosen
Hellen is a figure in Greek mythology regarded as the legendary ancestor and eponymous founder of the Hellenes (Greeks).
-
B.
Helene
Helene is the given name of Leni Riefenstahl, the controversial German filmmaker and actress known for her propaganda films during the Nazi era.
-
C.
Helene
Helene is a feminine given name of Greek origin, derived from Helen and associated with meanings like "light" or "torch."
-
D.
Hellenica
Hellenica is an ancient Greek historical work by Xenophon that continues Thucydides’ account, covering Greek history from 411 to 362 BCE.
-
E.
Hellanodikai
The Hellanodikai were the ancient Greek judges and officials responsible for overseeing and enforcing the rules of the Olympic Games at Olympia.
- 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_69ad8b21a62881908ec5dd4fba4a187c |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9abea8f4819090554d7319778170 |
completed | March 8, 2026, 3:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b1deb9c9548190b3d36803432b84f6 |
completed | March 11, 2026, 9:29 p.m. |
Created at: March 8, 2026, 3 p.m.