Triple
T13114556
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eli Roth |
E311059
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Eli |
E85994
|
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: Eli | Statement: [Eli Roth, givenName, Eli]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eli Context triple: [Eli Roth, givenName, Eli]
-
A.
Eli
chosen
Eli is a given name most famously associated with American inventor Eli Whitney, known for creating the cotton gin.
-
B.
Eli
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 a central character in Robert Silverberg’s science fiction novel "The Book of Skulls," one of four college students who seek an ancient brotherhood promising immortality at a terrible cost.
-
D.
Eli
Eli is the mysterious, centuries-old child vampire at the center of the Swedish horror film "Let the Right One In."
-
E.
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.
- 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_69d806a872d08190a329806f8ff30df4 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98180b6ac8190ae5a1f7c1480bd54 |
completed | April 10, 2026, 11:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6e28105c481908781775ba489c296 |
completed | May 3, 2026, 5:52 a.m. |
Created at: April 9, 2026, 9:06 p.m.