Triple
T21422723
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nona |
E528475
|
entity |
| Predicate | hasCompanion |
P22642
|
FINISHED |
| Object | Morta |
—
|
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: Morta | Statement: [Nona, hasCompanion, Morta]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Morta Context triple: [Nona, hasCompanion, Morta]
-
A.
Morta
chosen
Morta is the Roman goddess of death and destiny, one of the three Fates who determines the moment of each mortal’s death by cutting the thread of life.
-
B.
Mortus
Mortus is the main villain of the 1995 Sega Genesis beat ’em up game Comix Zone, a demonic comic-book creator who brings his own drawings to life to battle the hero.
-
C.
Malemort
Malemort is a commune in the Corrèze department of south-central France, situated near the town of Brive-la-Gaillarde.
-
D.
Toten
Toten is a traditional rural district in eastern Norway known for its agriculture and scenic landscape, located within Innlandet county.
-
E.
Mort
Mort is a comic fantasy novel in Terry Pratchett’s Discworld series that follows a young apprentice to Death himself.
- 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_69e0c455f3688190810bc96365791b0f |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ee8139ce848190b812d6d07f1bdef8 |
completed | April 26, 2026, 9:18 p.m. |
Created at: April 16, 2026, 5:48 p.m.