Triple
T194567
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gillette Stadium |
E3790
|
entity |
| Predicate | previousSurface |
P3424
|
FINISHED |
| Object | natural grass |
—
|
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: natural grass | Statement: [Gillette Stadium, previousSurface, natural grass]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousSurface Context triple: [Gillette Stadium, previousSurface, natural grass]
-
A.
previousGround
chosen
Indicates that one entity is the immediately preceding ground or surface state relative to another in a sequence or progression.
-
B.
previousTitle
Indicates that one title held or used by an entity directly preceded another title in sequence or time.
-
C.
surfaceType
Indicates the kind or classification of surface associated with an entity or interaction.
-
D.
previousDenomination
Indicates that one entity was the earlier or former denomination (name, value, or classification) of another entity in a sequence of denominations.
-
E.
previousCurrency
Indicates that one currency served as the predecessor or was replaced by another currency in a monetary system or sequence.
- 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_69a2548debd48190ae3a06d6e65b53c6 |
completed | Feb. 28, 2026, 2:35 a.m. |
| NER | Named-entity recognition | batch_69a25969425081908e178db8ba4631c2 |
completed | Feb. 28, 2026, 2:56 a.m. |
| PD | Predicate disambiguation | batch_69a256769ad8819083c1d83082c0215e |
completed | Feb. 28, 2026, 2:44 a.m. |
Created at: Feb. 28, 2026, 2:41 a.m.