Triple
T6927432
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Haabʼ |
E160346
|
entity |
| Predicate | hasCalendarRoundCycleLength |
P27022
|
FINISHED |
| Object | 18980 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: 18980 days | Statement: [Haabʼ, hasCalendarRoundCycleLength, 18980 days]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCalendarRoundCycleLength Context triple: [Haabʼ, hasCalendarRoundCycleLength, 18980 days]
-
A.
hasSolarCalendarLength
Indicates that an entity’s solar calendar is characterized by a specific duration or number of days.
-
B.
hasCycleLength
chosen
Indicates that an entity participates in or exhibits a cycle whose duration or size is specified by the associated length value.
-
C.
hasRitualCalendarLength
Indicates the relationship between an entity and the specific duration or length of its ritual calendar.
-
D.
hasWeekLength
Indicates the duration of a week associated with an entity, typically expressed as a number of days.
-
E.
hasNumberOfWeekSystems
Indicates the relationship that specifies how many distinct week-based systems are associated with or used by a given entity.
- 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_69c6884d350081908d8a970e4d40ad78 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6da1bf2088190a8ccfa01d9a1efc5 |
completed | March 27, 2026, 7:27 p.m. |
| PD | Predicate disambiguation | batch_69c6d7bb577c81908ee8b415b4281f3d |
completed | March 27, 2026, 7:17 p.m. |
Created at: March 27, 2026, 2:27 p.m.