Triple
T37472275
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Halls of Atonement |
E931181
|
entity |
| Predicate | entranceFactionControl |
P188376
|
FINISHED |
| Object | Venthyr |
—
|
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: Venthyr | Statement: [Halls of Atonement, entranceFactionControl, Venthyr]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: entranceFactionControl Context triple: [Halls of Atonement, entranceFactionControl, Venthyr]
-
A.
entranceFaction
chosen
Indicates a relationship where a specific faction controls, guards, or is otherwise associated with an entrance or access point.
-
B.
hasEntranceControl
Indicates that an entity implements or is subject to mechanisms that regulate or control access to its entrance.
-
C.
entryControl
Indicates a relationship where one entity regulates or authorizes another entity’s access to a place, system, or resource.
-
D.
guardedEntranceTo
Indicates that one entity serves as a protective or controlling barrier for access to another entity’s entrance.
-
E.
entranceTrait
Indicates a characteristic or feature associated with how an entity enters or is accessed (e.g., through a particular type or style of entrance).
- 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_69f76ec2af148190897d101070d7f415 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbacaf54648190811ea33b34907e8e |
completed | May 6, 2026, 9:03 p.m. |
| PD | Predicate disambiguation | batch_69fba883f770819091059c6f6c6af9f7 |
completed | May 6, 2026, 8:45 p.m. |
Created at: May 3, 2026, 4:17 p.m.