Triple
T8300233
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Enuma Elish |
E194332
|
entity |
| Predicate | hasTitle |
P38
|
FINISHED |
| Object |
When on High
"When on High" is the traditional English rendering of the opening words and common title of the ancient Babylonian creation epic Enuma Elish.
|
E724549
|
NE FINISHED |
How this triple was built (4 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: When on High | Statement: [Enuma Elish, hasTitle, When on High]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: When on High Context triple: [Enuma Elish, hasTitle, When on High]
-
A.
How High
How High is a 2001 stoner comedy film starring Method Man and Redman as underachieving friends who use a supernatural strain of marijuana to succeed at Harvard University.
-
B.
So High
"So High" is an R&B/soul song by John Legend from his debut album "Get Lifted."
-
C.
So High
"So High" is a creative work associated with DeVon Harris, likely recognized as one of his most prominent or influential projects.
-
D.
If Not Higher
"If Not Higher" is a classic Yiddish short story by I. L. Peretz that gently satirizes religious hypocrisy while celebrating genuine piety and compassion.
-
E.
All Time High
"All Time High" is the romantic pop ballad performed by Rita Coolidge that serves as the theme song for the 1983 James Bond film "Octopussy."
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: When on High Triple: [Enuma Elish, hasTitle, When on High]
Generated description
"When on High" is the traditional English rendering of the opening words and common title of the ancient Babylonian creation epic Enuma Elish.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: When on High Target entity description: "When on High" is the traditional English rendering of the opening words and common title of the ancient Babylonian creation epic Enuma Elish.
-
A.
How High
How High is a 2001 stoner comedy film starring Method Man and Redman as underachieving friends who use a supernatural strain of marijuana to succeed at Harvard University.
-
B.
So High
"So High" is an R&B/soul song by John Legend from his debut album "Get Lifted."
-
C.
So High
"So High" is a creative work associated with DeVon Harris, likely recognized as one of his most prominent or influential projects.
-
D.
If Not Higher
"If Not Higher" is a classic Yiddish short story by I. L. Peretz that gently satirizes religious hypocrisy while celebrating genuine piety and compassion.
-
E.
All Time High
"All Time High" is the romantic pop ballad performed by Rita Coolidge that serves as the theme song for the 1983 James Bond film "Octopussy."
- F. None of above. chosen
Provenance (5 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_69ca82e50ebc81909aa7b260c76bd757 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb7e879c588190a6f95cf7795541ad |
completed | March 31, 2026, 7:57 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cd68bcb43081909e3a8a00947d03f2 |
completed | April 1, 2026, 6:49 p.m. |
| NEDg | Description generation | batch_69cd6d574ba88190a2538897d201d8c4 |
completed | April 1, 2026, 7:09 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69cd7e536724819095ad006bc0f013a4 |
completed | April 1, 2026, 8:21 p.m. |
Created at: March 30, 2026, 5:53 p.m.