Triple
T5168880
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Admiralty anchor |
E116625
|
entity |
| Predicate | hasFlukeOrientation |
P61920
|
FINISHED |
| Object | opposed flukes at the ends of the arms |
—
|
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: opposed flukes at the ends of the arms | Statement: [Admiralty anchor, hasFlukeOrientation, opposed flukes at the ends of the arms]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFlukeOrientation Context triple: [Admiralty anchor, hasFlukeOrientation, opposed flukes at the ends of the arms]
-
A.
hasOrientation
Indicates that one entity is positioned or directed in a specific spatial or conceptual alignment relative to a reference frame or another entity.
-
B.
hasFieldOrientation
Indicates that one entity has a specified directional or spatial orientation relative to a field (such as magnetic, electric, or visual field).
-
C.
hasRegionalOrientation
Indicates that an entity is oriented toward, focused on, or primarily associated with a specific geographic region.
-
D.
hasStripeOrientation
Indicates the directional arrangement or alignment of stripes present on an entity.
-
E.
hasRunwayOrientation
Indicates that a runway is aligned or oriented in a specific directional heading.
- 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_69bd445ff97c81909a2615cc56235470 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd794dd9988190922e138f2a9a3c62 |
completed | March 20, 2026, 4:43 p.m. |
| PD | Predicate disambiguation | batch_69bd77b36c008190b91011a9fa52b3d2 |
completed | March 20, 2026, 4:37 p.m. |
| PDg | Predicate description generation | batch_69bd78d6a1388190804dcf568ca92129 |
completed | March 20, 2026, 4:41 p.m. |
Created at: March 20, 2026, 1:45 p.m.