Triple
T16010001
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Subtle Knife |
E388312
|
entity |
| Predicate | alsoKnownAs |
P39
|
FINISHED |
| Object |
Æsahættr
Æsahættr is the legendary, reality-cutting blade central to Philip Pullman’s His Dark Materials trilogy, capable of slicing through any material and opening windows between worlds.
|
E1189691
|
NE FINISHED |
How this triple was built (4 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: Æsahættr | Statement: [The Subtle Knife, alsoKnownAs, Æsahættr]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Æsahættr Context triple: [The Subtle Knife, alsoKnownAs, Æsahættr]
-
A.
Erlingr
Erlingr is a variant form of the Scandinavian given name Erling, traditionally associated with Norse and Germanic origins.
-
B.
Halldór
Halldór is an Icelandic given name most famously borne by Nobel Prize–winning author Halldór Laxness.
-
C.
Hrœrekr
Hrœrekr is the Old Norse form of the name Rurik, the semi-legendary Varangian chieftain traditionally regarded as the founder of the Rurikid dynasty in early medieval Rus'.
-
D.
Hrólfr
Hrólfr, better known as Rollo, was a Viking leader who became the first ruler of Normandy in the early 10th century.
-
E.
Hjálmar
Hjálmar is a masculine given name of Old Norse origin, traditionally used in Scandinavian countries.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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: Æsahættr Triple: [The Subtle Knife, alsoKnownAs, Æsahættr]
Generated description
Æsahættr is the legendary, reality-cutting blade central to Philip Pullman’s His Dark Materials trilogy, capable of slicing through any material and opening windows between worlds.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Æsahættr Target entity description: Æsahættr is the legendary, reality-cutting blade central to Philip Pullman’s His Dark Materials trilogy, capable of slicing through any material and opening windows between worlds.
-
A.
Erlingr
Erlingr is a variant form of the Scandinavian given name Erling, traditionally associated with Norse and Germanic origins.
-
B.
Halldór
Halldór is an Icelandic given name most famously borne by Nobel Prize–winning author Halldór Laxness.
-
C.
Hrœrekr
Hrœrekr is the Old Norse form of the name Rurik, the semi-legendary Varangian chieftain traditionally regarded as the founder of the Rurikid dynasty in early medieval Rus'.
-
D.
Hrólfr
Hrólfr, better known as Rollo, was a Viking leader who became the first ruler of Normandy in the early 10th century.
-
E.
Hjálmar
Hjálmar is a masculine given name of Old Norse origin, traditionally used in Scandinavian countries.
- F. None of above. chosen
Provenance (5 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_69d86dabcb7c8190b6a39d6831d2fa1b |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1828f8c688190a6b365f9140cd2d8 |
completed | April 17, 2026, 12:45 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffcf24a9d8819083d7b11d71442da6 |
completed | May 10, 2026, 12:19 a.m. |
| NEDg | Description generation | batch_69ffd065cb948190b0ad7e89a12ce535 |
completed | May 10, 2026, 12:25 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ffd1a52de08190a7b283af83be1f42 |
completed | May 10, 2026, 12:30 a.m. |
Created at: April 10, 2026, 4:55 a.m.