Triple
T5469657
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jacob Vaark |
E122798
|
entity |
| Predicate | employs |
P7
|
FINISHED |
| Object | Lina |
E109668
|
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: Lina | Statement: [Jacob Vaark, employs, Lina]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lina Context triple: [Jacob Vaark, employs, Lina]
-
A.
Lina
chosen
Lina is a Native American servant in Toni Morrison’s novel *A Mercy*, whose history of displacement and resilience reflects the novel’s themes of slavery, colonialism, and survival in 17th-century America.
-
B.
Lina
Lina Heydrich was the wife of high-ranking Nazi official Reinhard Heydrich and a committed supporter of National Socialism in Germany.
-
C.
Lucina
Lucina is a woman known primarily as the mother of the Western Roman Emperor Anthemius.
-
D.
Lucina
Lucina is a central protagonist and time-traveling princess from the Fire Emblem series, best known for her masked identity "Marth" and pivotal role in Fire Emblem Awakening.
-
E.
Lilia
Lilia is a feminine given name, often considered a variant of Lily and associated with the elegance and symbolism of the lily flower.
- 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_69bd46459ff48190823377457bcf7128 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd921b65f48190af7fcf89140f9ba8 |
completed | March 20, 2026, 6:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf4893029081908a801c7a44872ebf |
completed | March 22, 2026, 1:40 a.m. |
Created at: March 20, 2026, 2:09 p.m.