Triple
T37209694
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battlestar Galactica: HUMAN vs. CYLON |
E922265
|
entity |
| Predicate | themeLicenseHolder |
P15136
|
FINISHED |
| Object | Universal Parks & Resorts |
—
|
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: Universal Parks & Resorts | Statement: [Battlestar Galactica: HUMAN vs. CYLON, themeLicenseHolder, Universal Parks & Resorts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: themeLicenseHolder Context triple: [Battlestar Galactica: HUMAN vs. CYLON, themeLicenseHolder, Universal Parks & Resorts]
-
A.
licenseFor
Indicates that one entity grants or holds formal permission or authorization for another entity to perform an activity, use a resource, or operate under specified conditions.
-
B.
licenseAuthor
Indicates that one entity is the author or originator of a license granted to another entity.
-
C.
brandLicenseFrom
Indicates that one entity holds a licensed right to use the brand owned or controlled by another entity.
-
D.
licensee
chosen
Indicates that one entity is authorized by another, through a license agreement, to use or exploit certain rights, property, or resources.
-
E.
coLicensedWith
Indicates that two or more entities share a common license or are authorized under the same licensing agreement.
- F. None of above.
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_69f76ea4849481909b4a3073efb0114c |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb55de3b9c8190a7656aeab3c3ffbc |
completed | May 6, 2026, 2:53 p.m. |
| PD | Predicate disambiguation | batch_69fb35bc92e08190bff447624e2df791 |
completed | May 6, 2026, 12:36 p.m. |
Created at: May 3, 2026, 4:15 p.m.