Triple
T15411726
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marseilles Lock and Dam |
E368609
|
entity |
| Predicate | riverMileOnIllinoisRiver |
P111954
|
FINISHED |
| Object | approximately 247 |
—
|
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: approximately 247 | Statement: [Marseilles Lock and Dam, riverMileOnIllinoisRiver, approximately 247]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: riverMileOnIllinoisRiver Context triple: [Marseilles Lock and Dam, riverMileOnIllinoisRiver, approximately 247]
-
A.
riverMileFromMouth
Indicates the distance, measured in river miles, from the river’s mouth upstream to a specific point along the river.
-
B.
riverMilepost
chosen
Indicates the specific distance or position along a river, measured in miles from a defined starting point.
-
C.
riverKilometerContext
Indicates the position or context of something along a river, measured in river kilometers from a defined reference point.
-
D.
riverMileBelowHooverDam
Indicates the position of a location along the river measured in miles downstream from Hoover Dam.
-
E.
hasApproxLengthAlongRiver
Indicates that an entity has an approximate measured length that follows the course of a river rather than a straight-line distance.
- 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_69d85a16c68c819099c1b547fbc87b32 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03ea600b48190a3dbca1a68a2a1cd |
completed | April 16, 2026, 1:43 a.m. |
| PD | Predicate disambiguation | batch_69ded27f45548190a6d2b1b85cb47444 |
completed | April 14, 2026, 11:49 p.m. |
Created at: April 10, 2026, 3:20 a.m.