Triple
T18272241
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zerah |
E437642
|
entity |
| Predicate | birthOrderRelativeToTwin |
P110861
|
FINISHED |
| Object | second-born |
—
|
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: second-born | Statement: [Zerah, birthOrderRelativeToTwin, second-born]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: birthOrderRelativeToTwin Context triple: [Zerah, birthOrderRelativeToTwin, second-born]
-
A.
positionInFamilyBirthOrder
Indicates the relative order in which a person was born within their family (e.g., first-born, middle child, last-born).
-
B.
twinOrder
chosen
Indicates the relative birth sequence or ordering between two twins within a twin pair.
-
C.
hasTwin
Indicates that one entity is a twin of another, sharing the same birth event or time with a sibling.
-
D.
hasTwinStatus
Indicates that an entity has a twin relationship or classification, such as being one of a pair of twins or having an associated twin counterpart.
-
E.
parentOfTwins
Indicates that one entity is the parent of two siblings who are twins.
- 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_69d8b914530c8190b4474d862a2b2a1b |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e5004f0e7c8190a7206e193012a2d3 |
completed | April 19, 2026, 4:18 p.m. |
| PD | Predicate disambiguation | batch_69e44fd81c788190b08c6be3b07a08c5 |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:34 a.m.