Triple
T27243751
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ZKF |
E687281
|
entity |
| Predicate | servesUndergroundStation |
P169742
|
FINISHED |
| Object | King’s Cross St Pancras Underground station |
—
|
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: King’s Cross St Pancras Underground station | Statement: [ZKF, servesUndergroundStation, King’s Cross St Pancras Underground station]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servesUndergroundStation Context triple: [ZKF, servesUndergroundStation, King’s Cross St Pancras Underground station]
-
A.
hasNearbyUndergroundStationEntrance
Indicates that one entity is located close to an entrance of an underground (subway/metro) station.
-
B.
subwayStation
Indicates that one entity is a subway station associated with, located in, or serving the other entity.
-
C.
subwayServiceAtNearbyStation
chosen
Indicates that there is subway service available at a station located near the referenced place or entity.
-
D.
hasUndergroundFeatureNearby
Indicates that an entity is located close to an underground feature (such as a tunnel, cave, or buried structure).
-
E.
hasSubwayStationEntrance
Indicates that one entity serves as an entrance or access point to a subway station associated with another entity.
- 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_69ef355547408190b5ca0d777c65040a |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69fbc9d1dba881908c399b8e1dc13ce2 |
completed | May 6, 2026, 11:08 p.m. |
| PD | Predicate disambiguation | batch_69fbc8ec03ac8190a757563f96fab283 |
completed | May 6, 2026, 11:04 p.m. |
Created at: April 27, 2026, 10:39 a.m.