Triple
T11731286
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ZYN |
E278901
|
entity |
| Predicate | isPlaced |
P79614
|
FINISHED |
| Object | between gum and lip |
—
|
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: between gum and lip | Statement: [ZYN, isPlaced, between gum and lip]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isPlaced Context triple: [ZYN, isPlaced, between gum and lip]
-
A.
hasPlaceIn
Indicates that one entity occupies, is located within, or holds a specific position in another entity or context.
-
B.
isPositionedAs
chosen
Indicates that one entity is placed or arranged in a specific spatial or conceptual position relative to another.
-
C.
previouslyPlacedInOrder
Indicates that an item or entity has already been included in a prior order before the current context or transaction.
-
D.
canBePlacedUnder
Indicates that one entity is allowed or able to be positioned beneath another entity in a spatial or structural arrangement.
-
E.
isInPlace
Indicates that one entity is located within, at, or occupying the position of a specified place or location.
- 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_69d6aaffec6881908bead509e8621742 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a4d94de08190a7184cf26d8cb94e |
completed | April 10, 2026, 7:20 a.m. |
| PD | Predicate disambiguation | batch_69d88a7f51248190bf492bd7509b5413 |
completed | April 10, 2026, 5:28 a.m. |
Created at: April 8, 2026, 9:41 p.m.