Triple
T35312893
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USS Enterprise (NCC-1701-C) |
E1019823
|
entity |
| Predicate | enemyInFinalBattle |
P4675
|
FINISHED |
| Object | Romulan Star Empire |
—
|
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: Romulan Star Empire | Statement: [USS Enterprise (NCC-1701-C), enemyInFinalBattle, Romulan Star Empire]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: enemyInFinalBattle Context triple: [USS Enterprise (NCC-1701-C), enemyInFinalBattle, Romulan Star Empire]
-
A.
finalBossOf
Indicates that one entity serves as the ultimate or last major opponent or challenge that another entity must face or overcome.
-
B.
enemyCharacterIn
Indicates that a character is located within or present inside an enemy-controlled area, zone, or context.
-
C.
enemyCharacter
Indicates that one character is hostile or opposed to another, typically treating them as an adversary or foe.
-
D.
primaryEnemy
chosen
Indicates that one entity is the main or most significant adversary or opponent of another entity.
-
E.
deathSceneOpponent
Indicates the character, creature, or entity that directly opposes or confronts another at the moment or scene of that other entity’s death.
- 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_69f76de9d45c81908a2ed0956b448b65 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f7905842808190a4fc9917f0f4b60d |
completed | May 3, 2026, 6:13 p.m. |
| PD | Predicate disambiguation | batch_69f78e2f52e08190a77661223a96c601 |
completed | May 3, 2026, 6:04 p.m. |
Created at: May 3, 2026, 4:03 p.m.