Triple
T36410851
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Percy Gibson |
E896874
|
entity |
| Predicate | relativeAgeDifference |
P125146
|
FINISHED |
| Object | younger than Joan Collins |
—
|
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: younger than Joan Collins | Statement: [Percy Gibson, relativeAgeDifference, younger than Joan Collins]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relativeAgeDifference Context triple: [Percy Gibson, relativeAgeDifference, younger than Joan Collins]
-
A.
relativeAgeStatus
chosen
Indicates a comparative relationship specifying how the age of one entity relates to the age of another (e.g., older, younger, or same age).
-
B.
relativeAgeInference
Indicates an inferred ordering of ages between entities, specifying which one is relatively older or younger based on available information.
-
C.
hasRelativeAge
Indicates that one entity has an age that is defined or compared in relation to the age of another entity.
-
D.
relativeByBirth
Indicates that two entities are related to each other through a biological family connection established by birth.
-
E.
countsYearsFrom
Indicates a temporal relationship where the number of years is measured starting from a specified reference point or event.
- 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_69f76e54ce408190849acc3f7758937c |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a037c8d06cc8190ab6a5e18d9d2571e |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a0a54cc8190868c1bfa1590d1a6 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:10 p.m.