Triple
T15238522
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Giganotosaurus |
E364192
|
entity |
| Predicate | livedInEpoch |
P3869
|
FINISHED |
| Object | Late Cretaceous epoch |
—
|
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: Late Cretaceous epoch | Statement: [Giganotosaurus, livedInEpoch, Late Cretaceous epoch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: livedInEpoch Context triple: [Giganotosaurus, livedInEpoch, Late Cretaceous epoch]
-
A.
livedBefore
Indicates that one entity existed or was alive at an earlier time than another entity.
-
B.
livedDuring
chosen
Indicates that the subject existed or was alive at some point within the time period or lifespan associated with the object.
-
C.
livedApproximately
Indicates that an entity’s lifespan or period of residence is known only roughly, with approximate rather than exact dates.
-
D.
centuryLivedIn
Indicates the century during which an entity (typically a person) was alive or primarily active.
-
E.
positionInEra
Indicates the temporal placement or role of something within a specific historical or chronological era.
- 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_69d85a0dde7481908fc64d1e82d5d20d |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e007da7e988190925a9b67b8070bc7 |
completed | April 15, 2026, 9:49 p.m. |
| PD | Predicate disambiguation | batch_69deca899d5c8190be4a7c71e1683c69 |
completed | April 14, 2026, 11:15 p.m. |
Created at: April 10, 2026, 3:12 a.m.