Triple
T7855597
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Manggarai people |
E182166
|
entity |
| Predicate | riceFieldPattern |
P4754
|
FINISHED |
| Object | circular spiderweb-like fields |
—
|
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: circular spiderweb-like fields | Statement: [Manggarai people, riceFieldPattern, circular spiderweb-like fields]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: riceFieldPattern Context triple: [Manggarai people, riceFieldPattern, circular spiderweb-like fields]
-
A.
riceType
Indicates the specific variety or classification of rice associated with an entity.
-
B.
numberOfRiceStalks
Indicates the quantity or count of rice stalks associated with a given entity or context.
-
C.
yieldRelativeToOryza sativa
Indicates the comparative yield performance of an entity relative to that of *Oryza sativa* (cultivated rice).
-
D.
JapaneseFormation
Indicates a relationship where something is formed, created, or organized according to Japanese style, methods, or origin.
-
E.
fieldPattern
chosen
Indicates a recurring or structured arrangement or configuration present within a field or area.
- 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_69ca82869ee08190b8f9040dbc2c0467 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb1a74592c8190b42f298e3e33617b |
completed | March 31, 2026, 12:51 a.m. |
| PD | Predicate disambiguation | batch_69cae92180f88190ae3d44c3de7adc93 |
completed | March 30, 2026, 9:20 p.m. |
Created at: March 30, 2026, 4:52 p.m.