Triple
T6993567
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hancock, Massachusetts |
E162143
|
entity |
| Predicate | hasOutdoorResource |
P74338
|
FINISHED |
| Object | trails |
—
|
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: trails | Statement: [Hancock, Massachusetts, hasOutdoorResource, trails]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOutdoorResource Context triple: [Hancock, Massachusetts, hasOutdoorResource, trails]
-
A.
hasOutdoorFocus
Indicates a relationship where an entity is primarily concerned with, oriented toward, or specialized in outdoor environments, activities, or contexts.
-
B.
isOutdoor
Indicates that an entity or activity takes place outside, in an open-air or non-enclosed environment.
-
C.
hasOutdoorExhibits
Indicates that a place or institution includes exhibits or displays located in outdoor or open-air areas.
-
D.
outdoorVenue
Indicates that an event, activity, or gathering takes place at a location situated outdoors rather than inside a building or enclosed structure.
-
E.
outdoorSection
Indicates that one entity is a section, area, or portion that is located outdoors or in an open-air environment relative to another entity.
- F. None of above. chosen
Provenance (4 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_69c68856d7808190ab33ee914640281b |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6dbeaa88c8190a49f8504c1793e1f |
completed | March 27, 2026, 7:35 p.m. |
| PD | Predicate disambiguation | batch_69c6d7c4a18881908d267137daed828b |
completed | March 27, 2026, 7:17 p.m. |
| PDg | Predicate description generation | batch_69c6dbbc00fc8190a18221524b774021 |
completed | March 27, 2026, 7:34 p.m. |
Created at: March 27, 2026, 2:32 p.m.