Triple
T9737378
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ghent Altarpiece |
E236097
|
entity |
| Predicate | depicts |
P1581
|
FINISHED |
| Object | Eve |
E262928
|
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: Eve | Statement: [Ghent Altarpiece, depicts, Eve]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eve Context triple: [Ghent Altarpiece, depicts, Eve]
-
A.
Eve
Eve is one of the immortal, cultured vampire protagonists in Jim Jarmusch’s film "Only Lovers Left Alive," known for her wisdom, serenity, and deep love for her partner Adam.
-
B.
Eve
chosen
Eve is a bronze sculpture by Auguste Rodin depicting the biblical figure at the moment of shame and awakening after the Fall.
-
C.
Eve
Eve is a cigarette brand historically marketed by Liggett & Myers, known for its slim, fashion-oriented design targeting women smokers.
-
D.
Eve
Eve is the central protagonist of the film "Life-Size," a fashion doll magically brought to life who must navigate the real world while helping a young girl cope with personal challenges.
-
E.
Eve
Eve is a fictional artificial intelligence character from the web series "Video Game High School" and its associated media.
- 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_69ca84d313e88190983ee6ffd0ef60d2 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9ef032088190acd94c35b89e48b7 |
completed | April 1, 2026, 10:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1afd74a308190ae1a618bab5f7841 |
completed | April 5, 2026, 12:41 a.m. |
Created at: March 30, 2026, 8:22 p.m.