Triple
T37513211
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adria's hut |
E932566
|
entity |
| Predicate | belongsToFactionOrSide |
P25766
|
FINISHED |
| Object | human magic users |
—
|
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: human magic users | Statement: [Adria's hut, belongsToFactionOrSide, human magic users]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: belongsToFactionOrSide Context triple: [Adria's hut, belongsToFactionOrSide, human magic users]
-
A.
hasFaction
chosen
Indicates that an entity is affiliated with, belongs to, or is represented by a particular faction or group.
-
B.
hasOpposingFaction
Indicates that one faction stands in opposition or conflict to another faction.
-
C.
belongsToPartySide
Indicates that an entity is affiliated with or aligned to a particular side or faction within a party or group.
-
D.
hasCombatantSide
Indicates a relationship where a conflict, battle, or war is associated with one of the participating sides or factions involved in the combat.
-
E.
associatedWithDynastyOrFaction
Indicates that an entity is linked to, belongs to, or is significantly connected with a particular dynasty or faction.
- 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_69f76ec730988190b5aa4f9cb9afd518 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a002f0839fc8190a874d3b0d0826d7e |
completed | May 10, 2026, 7:08 a.m. |
| PD | Predicate disambiguation | batch_6a002eae7b6481909974b321e2789b7e |
completed | May 10, 2026, 7:07 a.m. |
Created at: May 3, 2026, 4:17 p.m.