Triple
T4472044
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hyena-swine |
E98515
|
entity |
| Predicate | alignmentWithMoreau |
P56739
|
FINISHED |
| Object | hostile |
—
|
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: hostile | Statement: [Hyena-swine, alignmentWithMoreau, hostile]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: alignmentWithMoreau Context triple: [Hyena-swine, alignmentWithMoreau, hostile]
-
A.
alignedAgainst
Indicates that two or more entities are united in opposition to a common target, side, or objective.
-
B.
alignmentConcept
Indicates a conceptual or abstract relationship of alignment or correspondence between entities, such as agreement, compatibility, or shared orientation in some dimension.
-
C.
alignsWith
Indicates that one entity is in agreement, harmony, or consistent correspondence with another in terms of position, direction, standard, or principle.
-
D.
basedOnAlignmentOf
Indicates a relationship where one entity is determined, derived, or decided according to how closely it aligns with another entity’s position, orientation, or criteria.
-
E.
originallyAlignedWith
Indicates that an entity was initially in agreement, support, or association with another entity or group, regardless of any later changes in stance or affiliation.
- F. None of above. chosen
Provenance (4 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_69b3454b4ae481908967426dd37284d6 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b356fb69a0819099f0005779f4fcac |
completed | March 13, 2026, 12:14 a.m. |
| PD | Predicate disambiguation | batch_69b3563bf4f8819081726cde3a34460b |
completed | March 13, 2026, 12:11 a.m. |
| PDg | Predicate description generation | batch_69b356f9afc48190acb50c45a310e072 |
completed | March 13, 2026, 12:14 a.m. |
Created at: March 12, 2026, 11:35 p.m.