Triple
T17961889
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Quarrel (Ian Fleming novels) |
E449103
|
entity |
| Predicate | helpsIn |
P129918
|
FINISHED |
| Object | investigation of Mr. Big |
—
|
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: investigation of Mr. Big | Statement: [Quarrel (Ian Fleming novels), helpsIn, investigation of Mr. Big]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: helpsIn Context triple: [Quarrel (Ian Fleming novels), helpsIn, investigation of Mr. Big]
-
A.
especiallyHelpsWhen
Indicates that one entity is particularly beneficial or effective in assisting another entity or situation under certain conditions or circumstances.
-
B.
laterHelps
Indicates that one entity provides help or assistance to another at a subsequent time rather than immediately.
-
C.
oftenHelps
Indicates that one entity frequently provides assistance or support to another.
-
D.
helpsBuild
Indicates that one entity assists or contributes to the construction, creation, or development of another entity.
-
E.
helpsIdentify
Indicates a relationship where one entity serves to distinguish, recognize, or determine the identity or characteristics of another entity.
- 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_69d8b9f8cca8819099836916c56b7c95 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4b132cc10819088526a0b4b098d69 |
completed | April 19, 2026, 10:40 a.m. |
| PD | Predicate disambiguation | batch_69e3f8f2bd088190b1e22ad4d9cc8b13 |
completed | April 18, 2026, 9:34 p.m. |
| PDg | Predicate description generation | batch_69e42d8d68288190a05dc5d7803cf823 |
completed | April 19, 2026, 1:19 a.m. |
Created at: April 10, 2026, 10:22 a.m.