Triple
T2771389
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | "Pretty" Ricky Conlan |
E61462
|
entity |
| Predicate | antagonistOf |
P18963
|
FINISHED |
| Object | Adonis Creed |
E61461
|
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: Adonis Creed | Statement: ["Pretty" Ricky Conlan, antagonistOf, Adonis Creed]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Adonis Creed Context triple: ["Pretty" Ricky Conlan, antagonistOf, Adonis Creed]
-
A.
Adonis Creed
chosen
Adonis Creed is a fictional professional boxer and the son of Apollo Creed, serving as the central protagonist of the Rocky spin-off and sequel film series Creed.
-
B.
Gage Creed
Gage Creed is a young boy whose tragic death and supernatural resurrection drive the central horror and emotional conflict in Stephen King’s novel "Pet Sematary."
-
C.
Adnis Reeves
Adnis Reeves is the late grandfather of Rumi Carter and the father of rapper and entrepreneur Jay-Z.
-
D.
Ezekiel Jones
Ezekiel Jones is a charming, tech-savvy master thief and one of the main Librarians in the fantasy adventure TV series "The Librarians."
-
E.
Kasseem Daoud Dean
Kasseem Daoud Dean is an American record producer, rapper, and entrepreneur better known by his stage name Swizz Beatz.
- 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_69ab4b7cd13481909174bca9809ed259 |
completed | March 6, 2026, 9:47 p.m. |
| NER | Named-entity recognition | batch_69abdd6a23208190ba94c9a9f601a042 |
completed | March 7, 2026, 8:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69afce89a144819096f9230c8d95ce3f |
completed | March 10, 2026, 7:55 a.m. |
Created at: March 6, 2026, 9:57 p.m.