Triple
T16579000
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ermine Street |
E402788
|
entity |
| Predicate | followsTerrain |
P103580
|
FINISHED |
| Object | lowland route through eastern England |
—
|
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: lowland route through eastern England | Statement: [Ermine Street, followsTerrain, lowland route through eastern England]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: followsTerrain Context triple: [Ermine Street, followsTerrain, lowland route through eastern England]
-
A.
isTerrainFollowing
Indicates that an object or path maintains a constant relative position or altitude with respect to the underlying terrain surface.
-
B.
involvesTerrain
chosen
Indicates that the relationship or action takes place in, across, or is directly affected by a specified type of terrain or landform.
-
C.
locatedOnTerrain
Indicates that one entity is physically situated on or atop a particular terrain surface.
-
D.
hasTerrainFor
Indicates that a location or area possesses terrain suitable or designated for a particular use, activity, or feature.
-
E.
hasRockyTerrain
Indicates that the subject possesses or is characterized by rough, uneven, or rock-covered ground or surface conditions.
- 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_69d88387363c8190a97a0c942130de97 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e3595f9be88190b01ba628ecf1103d |
completed | April 18, 2026, 10:13 a.m. |
| PD | Predicate disambiguation | batch_69e296a7d9d0819088555bca6c936e79 |
completed | April 17, 2026, 8:23 p.m. |
Created at: April 10, 2026, 5:16 a.m.