Triple
T27222993
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Goodge Street station |
E681329
|
entity |
| Predicate | hasDeepLevelShelter |
P3789
|
FINISHED |
| Object |
Goodge Street deep-level shelter
Goodge Street deep-level shelter is a World War II-era underground air-raid shelter in London, built beneath Goodge Street station and later used for military and civil defense purposes.
|
E1759391
|
NE FINISHED |
How this triple was built (3 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: Goodge Street deep-level shelter | Statement: [Goodge Street station, hasDeepLevelShelter, Goodge Street deep-level shelter]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Goodge Street deep-level shelter Triple: [Goodge Street station, hasDeepLevelShelter, Goodge Street deep-level shelter]
Generated description
Goodge Street deep-level shelter is a World War II-era underground air-raid shelter in London, built beneath Goodge Street station and later used for military and civil defense purposes.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDeepLevelShelter Context triple: [Goodge Street station, hasDeepLevelShelter, Goodge Street deep-level shelter]
-
A.
hasHardenedShelters
Indicates that an entity possesses or is equipped with shelters that are reinforced or hardened for protection.
-
B.
isSheltered
Indicates that one entity provides or serves as protective cover or refuge for another entity.
-
C.
hasShelters
chosen
Indicates that one entity provides, contains, or is associated with one or more shelters for another entity or purpose.
-
D.
hasShelteredAreas
Indicates that one entity provides or contains areas that offer protection or cover for another entity.
-
E.
hasShelteredEntrances
Indicates that an entity provides one or more entrances that are covered or protected from weather or external exposure.
- F. None of above.
Provenance (6 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_69eefac9f64c8190a07490fe0c8b72a3 |
completed | April 27, 2026, 5:57 a.m. |
| NER | Named-entity recognition | batch_69f757898fe48190b124dc7301672623 |
completed | May 3, 2026, 2:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a1253ae817c819082f128a85b3f0cbe |
completed | May 24, 2026, 1:26 a.m. |
| NEDg | Description generation | batch_6a1254e8f94881908407699a6fb433b9 |
completed | May 24, 2026, 1:31 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a125570e034819080d1b31fe17df8ba |
completed | May 24, 2026, 1:33 a.m. |
| PD | Predicate disambiguation | batch_69f754c484348190948d2a04ff228fb1 |
completed | May 3, 2026, 1:59 p.m. |
Created at: April 27, 2026, 9:43 a.m.