Triple
T38588120
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deeprun Tram to Stormwind City |
E932390
|
entity |
| Predicate | connectsZone |
P197852
|
FINISHED |
| Object | City of Ironforge |
—
|
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: City of Ironforge | Statement: [Deeprun Tram to Stormwind City, connectsZone, City of Ironforge]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectsZone Context triple: [Deeprun Tram to Stormwind City, connectsZone, City of Ironforge]
-
A.
connectsZones
chosen
Indicates a relationship where one zone is linked or joined to another, allowing interaction, transfer, or continuity between them.
-
B.
connectsArea
Indicates that one area serves as a link or passage between two other areas, enabling movement or interaction between them.
-
C.
connectsAreaNear
Indicates that one entity serves as a link or passage between areas that are geographically close to each other.
-
D.
connectsCentralAreaTo
Indicates a relationship where one element serves as a link or pathway between a central area and another location or component.
-
E.
connectsLocation
Indicates a relationship where one entity serves as a link or route that joins or provides access between two locations.
- 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_69f76ec654d48190b421111cf26e54d9 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a00262d71488190a769783fb09e5803 |
completed | May 10, 2026, 6:31 a.m. |
| PD | Predicate disambiguation | batch_6a0023985f148190a335a3fb93e9981e |
completed | May 10, 2026, 6:20 a.m. |
Created at: May 3, 2026, 4:32 p.m.