Triple
T28987311
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nyarlathotep |
E734721
|
entity |
| Predicate | numberOfAvatars |
P112247
|
FINISHED |
| Object | Thousand (often described as "a thousand forms") |
—
|
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: Thousand (often described as "a thousand forms") | Statement: [Nyarlathotep, numberOfAvatars, Thousand (often described as "a thousand forms")]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfAvatars Context triple: [Nyarlathotep, numberOfAvatars, Thousand (often described as "a thousand forms")]
-
A.
numberOfAvatarsDescribed
chosen
Indicates the count of distinct avatars that are described in a given context or data record.
-
B.
numberOfMoai
Indicates the quantity or count of Moai associated with a given subject.
-
C.
numberOfCharacters
Indicates the total count of individual characters present in a given text, string, or entity’s representation.
-
D.
numberOfPOVCharacters
Indicates the total count of distinct point-of-view characters associated with a given narrative or work.
-
E.
numberOfFaces
Indicates the relationship that specifies how many faces a given object or entity has.
- 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_69f05b0dd9b481908b7901e1c95ff6b2 |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69ffbb1c5bf88190a0bf791213045885 |
completed | May 9, 2026, 10:54 p.m. |
| PD | Predicate disambiguation | batch_69ffba0ab0f881908f84ef81f7a1bfe8 |
completed | May 9, 2026, 10:49 p.m. |
Created at: April 28, 2026, 9:15 a.m.