Triple
T23100261
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kryptonian |
E576004
|
entity |
| Predicate | notableMember |
P10
|
FINISHED |
| Object | Ursa |
—
|
NE NERFINISHED |
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: Ursa | Statement: [Kryptonian, notableMember, Ursa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ursa Context triple: [Kryptonian, notableMember, Ursa]
-
A.
Ursa
chosen
Ursa is a Kryptonian supervillain from the Superman franchise, known as a ruthless ally of General Zod and enemy of Superman.
-
B.
Pégomas
Pégomas is a commune in the Alpes-Maritimes department in southeastern France, known for its perfume flower cultivation and proximity to the French Riviera.
-
C.
Tauri
Tauri were an ancient people of the Crimean Peninsula, known from Greek and Roman sources for their distinct culture and coastal strongholds around the Black Sea.
-
D.
Ulzana
Ulzana is a ruthless and cunning Apache war leader whose violent campaign against settlers drives the central conflict of the Western film "Ulzana's Raid."
-
E.
Tisma
Tisma is a small rural municipality in Nicaragua known for its agricultural economy and traditional Central American community life.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245c060b48190a9bd61a47a16db17 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18de81060819084ab618f05aae583 |
completed | April 29, 2026, 4:49 a.m. |
Created at: April 17, 2026, 3:58 p.m.