Triple
T38374480
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vampire Coven |
E893578
|
entity |
| Predicate | mayConflictWith |
P4897
|
FINISHED |
| Object | rival vampire covens |
—
|
LITERAL 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: rival vampire covens | Statement: [Vampire Coven, mayConflictWith, rival vampire covens]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mayConflictWith Context triple: [Vampire Coven, mayConflictWith, rival vampire covens]
-
A.
conflictWith
chosen
Indicates that two entities are in opposition or disagreement, such that their goals, actions, or states are incompatible or interfere with each other.
-
B.
triggersConflict
Indicates that one entity initiates or causes a dispute, clash, or incompatibility to arise with another entity or within a system.
-
C.
mentionsConflict
Indicates that one entity refers to or discusses a dispute, disagreement, or conflict involving another entity.
-
D.
namedForConflict
Indicates that one entity is named after, or in commemoration of, a specific conflict, war, or battle.
-
E.
appliesToConflictWith
Indicates that one element’s scope, rules, or effects are relevant to a conflict involving another element, defining how that element is implicated in or governed by the conflict.
- 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_69f76e4b1f748190a380696a16eae4a2 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fcd1499e2c81909bafd84dc4810f45 |
completed | May 7, 2026, 5:52 p.m. |
| PD | Predicate disambiguation | batch_69fcccf024ec819086383ffbb6cfc036 |
completed | May 7, 2026, 5:33 p.m. |
Created at: May 3, 2026, 4:31 p.m.