Triple
T37513592
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spider Forest |
E932574
|
entity |
| Predicate | containsDungeonEntrance |
P6140
|
FINISHED |
| Object | Spider Cavern |
E2230580
|
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: Spider Cavern | Statement: [Spider Forest, containsDungeonEntrance, Spider Cavern]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: containsDungeonEntrance Context triple: [Spider Forest, containsDungeonEntrance, Spider Cavern]
-
A.
hasDungeon
Indicates that one entity possesses, contains, or includes a dungeon as part of its structure, property, or domain.
-
B.
hasEntrancesIn
Indicates that an entity has one or more entrances located within or opening into another specified entity or area.
-
C.
hasHiddenEntrance
Indicates that an entity possesses a concealed or non-obvious entrance or access point.
-
D.
hasEntrance
chosen
Indicates that one entity possesses or provides an entry point or access way to another entity or space.
-
E.
hasCaveEntranceDepth
Indicates the depth or vertical distance of a cave’s entrance relative to a reference level (such as ground surface or sea level).
- 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_69f76ec730988190b5aa4f9cb9afd518 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a01b241f7308190bedb7522cb5dc069 |
completed | May 11, 2026, 10:41 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a409efcf1dc8190af996121148fe50f |
completed | June 28, 2026, 4:11 a.m. |
| PD | Predicate disambiguation | batch_6a01b19ff12c81908ee1b188b4a3e118 |
completed | May 11, 2026, 10:38 a.m. |
Created at: May 3, 2026, 4:17 p.m.