Triple
T18616285
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lower Newton Falls hill |
E455028
|
entity |
| Predicate | positionInRace |
P16114
|
FINISHED |
| Object | late stage of Boston Marathon |
—
|
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: late stage of Boston Marathon | Statement: [Lower Newton Falls hill, positionInRace, late stage of Boston Marathon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionInRace Context triple: [Lower Newton Falls hill, positionInRace, late stage of Boston Marathon]
-
A.
positionOnRace
chosen
Indicates the relative ranking or placement an entity holds within the context of a race or competitive event.
-
B.
positionRelativeToTailrace
Indicates the spatial relationship of an entity’s location with respect to the tailrace (the downstream outflow area of a hydraulic or hydroelectric system).
-
C.
positionInRound
Indicates the specific ordinal place an entity occupies within a given round or sequence of rounds.
-
D.
positionOnCompetition
Indicates the ranking or place an entity holds within the results of a specific competition.
-
E.
positionOnLap
Indicates that one entity is physically situated resting on the lap area of 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_69d8d38bbe7c8190bdec3138e7d413c9 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e54d05da9c8190b8f4ef3a7a6deb05 |
completed | April 19, 2026, 9:45 p.m. |
| PD | Predicate disambiguation | batch_69e478cf5e888190a0b1074b0c6525df |
completed | April 19, 2026, 6:40 a.m. |
Created at: April 10, 2026, 11:46 a.m.