Triple
T36320645
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Groom, Texas |
E894321
|
entity |
| Predicate | roadsideAttraction |
P28518
|
FINISHED |
| Object | giant cross visible from Interstate 40 |
—
|
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: giant cross visible from Interstate 40 | Statement: [Groom, Texas, roadsideAttraction, giant cross visible from Interstate 40]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roadsideAttraction Context triple: [Groom, Texas, roadsideAttraction, giant cross visible from Interstate 40]
-
A.
roadsideFunction
Indicates that something serves a specific purpose or role related to the use, support, or operation of a roadside area.
-
B.
roadSide
chosen
Indicates that one entity is located along, beside, or immediately adjacent to a road.
-
C.
ridesAttraction
Indicates that an entity participates in experiencing or using an attraction, such as going on a ride at a venue or amusement location.
-
D.
relatedAttraction
Indicates that one attraction is associated with or connected to another attraction in some relevant way.
-
E.
recordAttraction
Indicates that an instance of an attraction (e.g., interest or appeal) is documented or logged as a record in relation to 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_69f76e4d1a788190a6ab6ccca28547a7 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7ba6d06f48190a71b5a2f19e2232f |
completed | May 3, 2026, 9:13 p.m. |
| PD | Predicate disambiguation | batch_69f7b9a4aad48190a62e41c5e39339d9 |
completed | May 3, 2026, 9:09 p.m. |
Created at: May 3, 2026, 4:09 p.m.