Triple
T37011803
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Destiny 2: Shadowkeep |
E915969
|
entity |
| Predicate | nonPlayerCharacter |
P45541
|
FINISHED |
| Object | Eris Morn |
—
|
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: Eris Morn | Statement: [Destiny 2: Shadowkeep, nonPlayerCharacter, Eris Morn]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nonPlayerCharacter Context triple: [Destiny 2: Shadowkeep, nonPlayerCharacter, Eris Morn]
-
A.
nonHumanCharacter
Indicates that the character involved in the relation is not a human being (e.g., an animal, creature, AI, or other non-human entity).
-
B.
notARealPerson
Indicates that the referenced entity is fictional, artificial, or otherwise not an actual human being in reality.
-
C.
hasNoHumanProtagonist
Indicates that in the described work or narrative, none of the main protagonists are human characters.
-
D.
coProtagonist
Indicates that two or more entities share the primary leading role together in the same narrative work.
-
E.
narrativeCharacter
chosen
Indicates that one entity functions as a character within the narrative or story associated with another entity.
- 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_69f76e90ed548190b187d2475f5c807d |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb154c0fe08190a2e41e7a29b6055f |
completed | May 6, 2026, 10:17 a.m. |
| PD | Predicate disambiguation | batch_69f9fecc005c8190be082a8689193745 |
completed | May 5, 2026, 2:29 p.m. |
Created at: May 3, 2026, 4:14 p.m.