Triple
T36711280
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | יְהוֹצָדָק |
E906799
|
entity |
| Predicate | isFromLineage |
P171863
|
FINISHED |
| Object |
line of Aaron
The line of Aaron is the hereditary priestly lineage in ancient Israel descending from Aaron, brother of Moses, from which the Jewish high priests and temple priests were traditionally drawn.
|
E2195653
|
NE FINISHED |
How this triple was built (3 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: line of Aaron | Statement: [יְהוֹצָדָק, isFromLineage, line of Aaron]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: line of Aaron Triple: [יְהוֹצָדָק, isFromLineage, line of Aaron]
Generated description
The line of Aaron is the hereditary priestly lineage in ancient Israel descending from Aaron, brother of Moses, from which the Jewish high priests and temple priests were traditionally drawn.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isFromLineage Context triple: [יְהוֹצָדָק, isFromLineage, line of Aaron]
-
A.
isLineageType
Indicates that one entity represents a type or category within the lineage or ancestral line of another entity.
-
B.
hasLineageCharacteristic
Indicates that an entity possesses a specific trait, feature, or quality that is inherited or derived from its lineage or ancestral line.
-
C.
isDescendantLineOf
chosen
Indicates that one entity is connected to another through a direct or indirect line of descent, such as child, grandchild, or further generational lineage.
-
D.
hasLineageMember
Indicates that one entity is a member or descendant within the lineage or ancestral line of another entity.
-
E.
hasLineageRole
Indicates a relationship where an entity holds a specific role or function within a lineage, ancestry, or genealogical chain.
- F. None of above.
Provenance (6 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_69f76e73ad108190a5241585f2303e9a |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f7c9f5a8848190ba956ff27f44e396 |
completed | May 3, 2026, 10:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3a3831190c81909db771fa0dcd5282 |
completed | June 23, 2026, 7:39 a.m. |
| NEDg | Description generation | batch_6a3a394dd37c8190a4980231c3eab440 |
completed | June 23, 2026, 7:44 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a3a3a7a76288190ab3266944842247f |
completed | June 23, 2026, 7:49 a.m. |
| PD | Predicate disambiguation | batch_69f7c8999a348190abc1895eaa6e036d |
completed | May 3, 2026, 10:13 p.m. |
Created at: May 3, 2026, 4:12 p.m.