Triple
T20946656
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Samuel |
E515859
|
entity |
| Predicate | servedUnder |
P258
|
FINISHED |
| Object | Eli the priest |
—
|
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: Eli the priest | Statement: [Samuel, servedUnder, Eli the priest]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eli the priest Context triple: [Samuel, servedUnder, Eli the priest]
-
A.
Isaac of Nineveh
Isaac of Nineveh was a 7th-century Syriac Christian bishop and mystic renowned for his influential writings on asceticism, prayer, and divine mercy.
-
B.
Eli
chosen
Eli is a biblical high priest and judge of Israel known for mentoring the prophet Samuel and presiding over the sanctuary at Shiloh.
-
C.
Eli
Eli is the mysterious, centuries-old child vampire at the center of the Swedish horror film "Let the Right One In."
-
D.
Eli
"Eli" is a 2019 Netflix horror film about a boy with a mysterious illness who undergoes experimental treatment in a secluded facility where sinister supernatural events unfold.
-
E.
Eli
Eli is a short form of the given name Elin, commonly used as a familiar or diminutive version of the name.
- 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_69e0b4fcd678819087a304291f14330a |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6fad97aa48190b4be692e3afce8c9 |
completed | April 21, 2026, 4:19 a.m. |
Created at: April 16, 2026, 12:56 p.m.