Triple
T4768141
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ahab |
E105861
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Jezebel |
E109896
|
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: Jezebel | Statement: [Ahab, spouse, Jezebel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jezebel Context triple: [Ahab, spouse, Jezebel]
-
A.
Jezebel
Jezebel is a feminist-leaning online magazine and blog known for its sharp commentary on gender, culture, and media.
-
B.
Jezebel
Jezebel is a 1938 American drama film starring Bette Davis as a headstrong Southern belle whose defiance leads to personal and social ruin.
-
C.
Jezebel
chosen
Jezebel is a notorious Phoenician queen in the Hebrew Bible, remembered for promoting Baal worship in Israel and for her violent conflict with the prophet Elijah.
-
D.
Delilah
Delilah is a biblical figure best known for betraying Samson by discovering and revealing the secret of his strength.
-
E.
Delilah
"Delilah" is a song by English indie rock band Florence and the Machine, featured on their 2015 album *How Big, How Blue, How Beautiful*.
- 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_69bd43f226fc8190b867cc249c2a9042 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6537eb80819096e0ae906c59d605 |
completed | March 20, 2026, 3:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be3a8f7318819088839becd09577ce |
completed | March 21, 2026, 6:28 a.m. |
Created at: March 20, 2026, 1:21 p.m.