Triple
T3091891
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mittelwerk underground factory |
E64499
|
entity |
| Predicate | reasonForUndergroundLocation |
P30171
|
FINISHED |
| Object | protection from Allied bombing |
—
|
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: protection from Allied bombing | Statement: [Mittelwerk underground factory, reasonForUndergroundLocation, protection from Allied bombing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reasonForUndergroundLocation Context triple: [Mittelwerk underground factory, reasonForUndergroundLocation, protection from Allied bombing]
-
A.
reasonForLocation
chosen
Indicates the cause, purpose, or justification for why an entity is at a particular location.
-
B.
transferredToLondonUnderground
Indicates that something or someone has been moved from a previous context or system into the London Underground network or organization.
-
C.
nearUndergroundLine
Indicates that one entity is located close in distance to an underground (subway/metro) line.
-
D.
hasUndergroundSection
Indicates that an entity includes a portion or segment that is located below ground level.
-
E.
hasUndergroundConnections
Indicates that one entity is linked to another through subterranean or hidden passageways, networks, or channels.
- 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_69ad857c97d88190b26f9b1c90839c77 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada20eeee88190a5eecfce10e3848c |
completed | March 8, 2026, 4:21 p.m. |
| PD | Predicate disambiguation | batch_69ad9ded78f881908be6fc0fb7c35764 |
completed | March 8, 2026, 4:03 p.m. |
Created at: March 8, 2026, 3:03 p.m.