Triple
T3567146
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Logan Killicks |
E75476
|
entity |
| Predicate | ageRelativeTo |
P43008
|
FINISHED |
| Object | older than Janie Crawford |
—
|
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: older than Janie Crawford | Statement: [Logan Killicks, ageRelativeTo, older than Janie Crawford]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ageRelativeTo Context triple: [Logan Killicks, ageRelativeTo, older than Janie Crawford]
-
A.
hasRelativeAge
chosen
Indicates that one entity has an age that is defined or compared in relation to the age of another entity.
-
B.
timeRelativeToBirth
Indicates the temporal position of an event or state relative to an entity’s birth (e.g., before, at, or after birth).
-
C.
ageProgression
Indicates a temporal relationship where an entity’s age increases or advances over time.
-
D.
ageStatus
Indicates the relationship between an entity and its classification into an age-related category or status (e.g., minor, adult, senior).
-
E.
agePattern
Indicates a relationship where entities share or follow a specific configuration, distribution, or rule regarding their ages.
- 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_69ad85d512708190829c8b2d3a2ccfb8 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc0ab51d881908f004fae47ab09d9 |
completed | March 8, 2026, 6:32 p.m. |
| PD | Predicate disambiguation | batch_69adb834779081908468e182d5f6cf02 |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:21 p.m.