Triple
T14023789
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mermnad dynasty |
E337402
|
entity |
| Predicate | namedAfter |
P63
|
FINISHED |
| Object | Gyges of Lydia |
E337398
|
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: Gyges of Lydia | Statement: [Mermnad dynasty, namedAfter, Gyges of Lydia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gyges of Lydia Context triple: [Mermnad dynasty, namedAfter, Gyges of Lydia]
-
A.
Gyges
Gyges is one of the three Hecatoncheires in Greek mythology, a primordial giant with a hundred hands and fifty heads who aided the Olympian gods in their battle against the Titans.
-
B.
Gyges
chosen
Gyges was an early 7th-century BCE king of Lydia, known from both Greek and Near Eastern sources for founding the Mermnad dynasty and dramatically seizing the throne.
-
C.
Candaules
Candaules was a legendary king of Lydia, best known from Herodotus’ account in which his murder by Gyges leads to the founding of a new royal dynasty.
-
D.
King Midas
King Midas is a legendary Phrygian king in Greek mythology best known for his fabled ability to turn everything he touched into gold.
-
E.
Midas
Midas is a powerful and aggressive robot boxer from the science-fiction film "Real Steel."
- 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_69d81c6543a48190bd5ba93d7419e797 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2f3d87b88190b038d334f4965369 |
completed | April 14, 2026, 12:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcd097814081909835aeed46aa4a59 |
completed | May 7, 2026, 5:49 p.m. |
Created at: April 9, 2026, 10:19 p.m.