Triple
T19614038
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vice Mayor of Davao City |
E470809
|
entity |
| Predicate | maximumConsecutiveYears |
P57614
|
FINISHED |
| Object | 9 years |
—
|
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: 9 years | Statement: [Vice Mayor of Davao City, maximumConsecutiveYears, 9 years]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maximumConsecutiveYears Context triple: [Vice Mayor of Davao City, maximumConsecutiveYears, 9 years]
-
A.
maximumConsecutiveTerms
Indicates the greatest number of terms that can occur in an unbroken, continuous sequence within a given context or structure.
-
B.
totalYearsLimit
chosen
Indicates the maximum total number of years allowed for the relevant activity, condition, or relationship.
-
C.
durationInYears
Indicates the length of time associated with something, measured in whole or fractional years.
-
D.
coversYearsTo
Indicates a temporal relationship where one entity spans, includes, or extends up to a specified year or range of years represented by the other entity.
-
E.
mostWinsYears
Indicates the years during which an entity achieved the highest number of wins compared to others or compared to its own performance in other years.
- 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_69d8e510fa248190b7afb274a1d4cf73 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e640ce272481909688527f72d2c976 |
completed | April 20, 2026, 3:05 p.m. |
| PD | Predicate disambiguation | batch_69e514e166dc8190a0f147e0b4c8bbe7 |
completed | April 19, 2026, 5:46 p.m. |
Created at: April 10, 2026, 1:43 p.m.