Triple
T1804853
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IR36 |
E40197
|
entity |
| Predicate | maturityDuration |
P32568
|
FINISHED |
| Object | about 105 days |
—
|
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: about 105 days | Statement: [IR36, maturityDuration, about 105 days]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maturityDuration Context triple: [IR36, maturityDuration, about 105 days]
-
A.
maturityRange
Indicates the span or limits of maturity (such as age, development stage, or readiness) within which the related entities or conditions are considered applicable.
-
B.
maturity
Indicates that an entity has reached a specified stage of development, completeness, or readiness, often marking the point at which certain rights, obligations, or behaviors become applicable.
-
C.
maximumBondMaturity
Indicates the longest allowable or actual time period until a bond tied to an entity reaches its maturity date.
-
D.
timeHorizonOfLoans
Indicates the length of time over which loans are scheduled to be outstanding or repaid.
-
E.
validityPeriodForAdults
Indicates the time span during which something is considered valid or applicable specifically for adults.
- F. None of above. chosen
Provenance (4 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_69a88643a3388190a612f2ebe1fb29e7 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69aba67721788190951beae25e885457 |
completed | March 7, 2026, 4:15 a.m. |
| PD | Predicate disambiguation | batch_69aa61d514c081908197ac1f7c7d7a88 |
completed | March 6, 2026, 5:10 a.m. |
| PDg | Predicate description generation | batch_69aba67554788190b429f2b9f0a70310 |
completed | March 7, 2026, 4:15 a.m. |
Created at: March 4, 2026, 7:32 p.m.