Triple
T3948588
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cassandra |
E84806
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Polyxena |
E322580
|
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: Polyxena | Statement: [Cassandra, sibling, Polyxena]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Polyxena Context triple: [Cassandra, sibling, Polyxena]
-
A.
Polyxena
chosen
Polyxena is a princess of Troy in Greek mythology, often associated with the hero Achilles and the tragic events surrounding the Trojan War.
-
B.
Polyxena
Polyxena is an alternate name for Olympias, the mother of Alexander the Great and a prominent queen of ancient Macedon.
-
C.
Creusa
Creusa is a figure in Greek mythology, often depicted as an Athenian princess and mother of Ion in Euripides’ tragedy.
-
D.
Athénaïs
Athénaïs was the familiar name of Madame de Montespan, the influential chief mistress of King Louis XIV of France and a prominent figure at the 17th-century French court.
-
E.
Hypsipyle
Hypsipyle is a figure in Greek mythology, the Lemnian princess and former queen who aided the Argonauts and is best known for her tragic and heroic role in various legends.
- 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_69aed934fbfc8190847068e4546de963 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aef910ecc08190a4fca89bcf063e0c |
completed | March 9, 2026, 4:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5339feb4c8190ad96a5680cb5294e |
completed | March 14, 2026, 10:08 a.m. |
Created at: March 9, 2026, 3:30 p.m.