Triple
T29106823
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Weiqi |
E736783
|
entity |
| Predicate | boardLinesOrientation |
P42939
|
FINISHED |
| Object | horizontal and vertical |
—
|
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: horizontal and vertical | Statement: [Weiqi, boardLinesOrientation, horizontal and vertical]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: boardLinesOrientation Context triple: [Weiqi, boardLinesOrientation, horizontal and vertical]
-
A.
lineOrientation
chosen
Indicates the directional alignment or angle of a line relative to a reference frame or axis.
-
B.
trailOrientation
Indicates the directional alignment or facing direction of a trail relative to a reference frame or compass directions.
-
C.
streetGridOrientation
Indicates the predominant directional alignment or pattern of streets within a given area or city layout.
-
D.
branchLineDirection
Indicates the directional orientation or flow of a branch line relative to a main line or reference point.
-
E.
yardLine
Indicates the specific position on a football field, measured in yards from a reference goal line, where a play or event occurs.
- 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_69f077ec765c81909474c88bcc8bab43 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f661ba062881909fa3d7b23938e2ab |
completed | May 2, 2026, 8:42 p.m. |
| PD | Predicate disambiguation | batch_69f65c2376a08190be5215171e908e69 |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 11:16 a.m.