Triple
T38620160
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tirisfal Glades |
E936844
|
entity |
| Predicate | primaryEnemyFactionPresence |
P189050
|
FINISHED |
| Object | Scarlet Crusade |
E2230055
|
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: Scarlet Crusade | Statement: [Tirisfal Glades, primaryEnemyFactionPresence, Scarlet Crusade]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryEnemyFactionPresence Context triple: [Tirisfal Glades, primaryEnemyFactionPresence, Scarlet Crusade]
-
A.
primaryEnemyForces
Indicates that the related entities constitute the main opposing or hostile forces in a conflict or competitive situation.
-
B.
enemyPresence
chosen
Indicates the presence of hostile or adversarial entities in relation to a specified entity or location.
-
C.
primaryEnemy
Indicates that one entity is the main or most significant adversary or opponent of another entity.
-
D.
hasOpposingFaction
Indicates that one faction stands in opposition or conflict to another faction.
-
E.
oppositeFactionArea
Indicates that the referenced area belongs to a faction that is opposed to the faction of the subject entity.
- F. None of above.
Provenance (4 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_69f76ed403208190b862dc795171353f |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c9141dc819098d7fcc36e69882c |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a42158362248190aa60d7501b164af2 |
completed | June 29, 2026, 6:49 a.m. |
| PD | Predicate disambiguation | batch_6a037a2026248190b894436a578d79ac |
completed | May 12, 2026, 7:06 p.m. |
Created at: May 3, 2026, 4:32 p.m.